# decision-making

Decision-making is the process of formulating options, establishing preferences, and making commitments, including through technical decision analysis and AI-related methods.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## AI is Changing the Cross-Platform Decision Matrix

DevFeed: [AI is Changing the Cross-Platform Decision Matrix](<https://devfeed.tech/articles/ai-is-changing-the-cross-platform-decision-matrix-146854.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/dotnet/ai-cross-platform-decision-matrix/>)

Author: David Ortinau

Published: 2026-11-20T18:00:00Z

Content type: article

Language: en

Sources: [.NET Blog](<https://devfeed.tech/sources/net-blog.md>)

Topics: [.NET MAUI](<https://devfeed.tech/topics/net-maui.md>), [.NET](<https://devfeed.tech/topics/net.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [app](<https://devfeed.tech/tags/app.md>), [blog](<https://devfeed.tech/tags/blog.md>), [build](<https://devfeed.tech/tags/build.md>), [choice](<https://devfeed.tech/tags/choice.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cross-platform](<https://devfeed.tech/tags/cross-platform.md>), [days](<https://devfeed.tech/tags/days.md>), [decision](<https://devfeed.tech/tags/decision.md>), [net](<https://devfeed.tech/tags/net.md>), [net-11](<https://devfeed.tech/tags/net-11.md>), [net-for-ios](<https://devfeed.tech/tags/net-for-ios.md>), [net-maui](<https://devfeed.tech/tags/net-maui.md>), [net-maui-controls](<https://devfeed.tech/tags/net-maui-controls.md>), [platform](<https://devfeed.tech/tags/platform.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

In this Barista Notes experiment, AI agents made a second platform UI practical to build, but maintaining it still required extra implementation and verification. Rewriting the Android and iOS interfaces in UIKit and Android Views over a shared C# core took under four hours of the author's time; adding one feature across both versions used about 1.4 times the worker model minutes of the .NET MAUI version and drew more defect and technical feedback. A coordinating agent's verification work exceeded the implementation workers' combined model time. Matched full ReadyToRun builds had faster measured startup and smaller packages for platform UI on both tested devices, but Android defaults changed the package-size tradeoff. Results depend on this app, configuration, and measurement method. The author recommends starting with one shared .NET MAUI UI, then testing platform UI on screens where measured needs justify the added per-platform testing, device checks, triage, and review.

### Source excerpt

AI agents rebuilt a .NET MAUI app with platform UI in days. See what that cost to build, what it costs to maintain, and what changed at runtime, so you can weigh the same choice for your app. The post AI is Changing the Cross-Platform Decision Matrix appeared first on .NET Blog.

## Incorporating argumentation frameworks for LLM decision-making: Task-specific design and evaluation

DevFeed: [Incorporating argumentation frameworks for LLM decision-making: Task-specific design and evaluation](<https://devfeed.tech/articles/incorporating-argumentation-frameworks-for-llm-decision-making-task-specific-design-and-evaluation-145502.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25361>)

Author: Bochen Han, Anshu Xiong, Mingyang Ma

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [arguments](<https://devfeed.tech/tags/arguments.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [design](<https://devfeed.tech/tags/design.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fact-verification](<https://devfeed.tech/tags/fact-verification.md>), [formal](<https://devfeed.tech/tags/formal.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [generative](<https://devfeed.tech/tags/generative.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [inference](<https://devfeed.tech/tags/inference.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-inference](<https://devfeed.tech/tags/llm-inference.md>), [llms](<https://devfeed.tech/tags/llms.md>), [model-selection](<https://devfeed.tech/tags/model-selection.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Argumentation frameworks do not reliably improve LLM decision-making across tasks; their design needs to fit the task. For debate-based decisions, Qnt-Arg groups arguments by original speaker and combines estimated argument strengths with candidate-answer priors using gradual semantics. It consistently outperformed other argumentation-augmented methods in matched configurations. For retrieval-based fact verification, Qlt-Arg uses credibility estimates to rank conflicting evidence, then grounded semantics to select evidence for LLM inference; it improved performance over the baselines. The study also examines how generative and decision models contribute to these methods. These findings are limited to the evaluated tasks and configurations.

### Source excerpt

arXiv:2611.25361v1 Announce Type: cross Abstract: Argumentation frameworks (AFs) provide explicit, formal mechanisms for representing and resolving conflicts and thus have been incorporated into large language model (LLM) decision-making. The benefits vary and depend on how arguments and their relations are constructed, evaluated, and incorporated into the decision process. {We abstract a workflow consisting of four stages based on existing argumentation-augmented methods} and investigate their design choices over tasks of debate-based decision-making and retrieval-based fact verification. Our evaluation with recent LLMs shows that existing methods do not consistently improve performance across the considered tasks. Motivated by this observation, we develop two task-specific methods. The first is called Qnt-Arg, which organizes arguments around the original speakers in debate materials and aggregates model-estimated argument strengths and candidate-answer priors under gradual semantics. The second is Qlt-Arg that uses credibility estimates to establish preferences between conflicting evidence items and applies grounded semantics to select acceptable evidence for subsequent LLM inference. We examine the roles of generative and decision models within the two methods. In the debate setting, Qnt-Arg consistently outperforms other argumentation-augmented methods across matched configurations; Qlt-Arg improves retrieval-based fact-verification performance compared with the baselines. These findings demonstrate the value of combining formal argumentation and LLM while highlighting the importance of aligning with tasks in argumentation construction, model selection, and the role of formal semantic reasoning.

## Sirius-Tiamat: How Small Can a One-Pass Decision Encoder Get Before Its Decisions Change?

DevFeed: [Sirius-Tiamat: How Small Can a One-Pass Decision Encoder Get Before Its Decisions Change?](<https://devfeed.tech/articles/sirius-tiamat-how-small-can-a-one-pass-decision-encoder-get-before-its-decisions-change-145659.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26339>)

Author: Mohammed Nayeem Khan, Vrishank Tiwari

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [scaling laws](<https://devfeed.tech/topics/scaling-laws.md>)

Tags: [bf16](<https://devfeed.tech/tags/bf16.md>), [bits](<https://devfeed.tech/tags/bits.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [distilling](<https://devfeed.tech/tags/distilling.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [error](<https://devfeed.tech/tags/error.md>), [exit](<https://devfeed.tech/tags/exit.md>), [laya](<https://devfeed.tech/tags/laya.md>), [layers](<https://devfeed.tech/tags/layers.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [pass](<https://devfeed.tech/tags/pass.md>), [question](<https://devfeed.tech/tags/question.md>), [scale](<https://devfeed.tech/tags/scale.md>), [schema](<https://devfeed.tech/tags/schema.md>), [size](<https://devfeed.tech/tags/size.md>), [student](<https://devfeed.tech/tags/student.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [temperature](<https://devfeed.tech/tags/temperature.md>)

### AI overview

The study finds that compression can preserve Laya's decisions to varying degrees, with results depending on method and evaluation set. On in-family versus out-of-family items, bf16 changed 0.2% versus 2.2% of decisions, 6-bit grouped rounding 1.3% versus 5.9%, and deleting six layers 0.9% versus 9.1%. Pruning also raised expected calibration error from 5.9% to 39.2%; a fitted temperature requiring no labels reduced it to 3.6%. A single scale per tensor failed below six bits, while CPU dynamic int8 changed 30% of decisions, nearly all through one layer. At equal stored size, rounding changed fewer decisions than deletion. Distillation reduced a 16-layer student's in-family flips from 44% to 9%, though out-of-family flips were 45%. The evidence is limited to synthetic, LLM-labelled data and one architecture.

### Source excerpt

arXiv:2611.26339v1 Announce Type: new Abstract: A one-pass decision encoder reads a text, a question and several named options, and returns a probability for each option in a single forward pass. We ask how far Laya, a 421M-parameter encoder of this kind, can be compressed before its decisions change. We count decisions that differ from Laya's own full-precision (fp32) answer, and track calibration (how well confidence matches accuracy, measured by expected calibration error, ECE), on 1,221 synthetic items with the training schemas, 273 with an unseen schema, and 800 out-of-family questions from ARC, MMLU and HellaSwag. Layer pruning of a related model family is known; we add flips, calibration, held-out data and retraining. bf16 changes 0.2% of in-family decisions but 2.2% out of family; 6-bit grouped rounding 1.3% and 5.9%; deleting 6 layers 0.9% and 9.1%, while ECE rises from 5.9% to 39.2%. One fitted temperature, needing no labels, restores it to 3.6%. One scale per tensor fails below six bits, and CPU dynamic int8 changes 30% of decisions, nearly all through one layer. Total variation tracks flips for rounding but not for deletion, and an early exit saves layers over a static cut only if its confidence gate is first recalibrated. Distilling a 16-layer student cuts its in-family flips from 44% to 9% (45% out of family). At equal stored size, rounding flips fewer decisions than deletion. Data are synthetic and LLM-labelled, for one architecture.

## What If Chain-of-Thought Is Not Enough?

DevFeed: [What If Chain-of-Thought Is Not Enough?](<https://devfeed.tech/articles/what-if-chain-of-thought-is-not-enough-145648.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26282>)

Author: Marc Jansen

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>)

Tags: [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [decision](<https://devfeed.tech/tags/decision.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

The paper tests whether LLMs' internal reasoning can be deliberately changed by fine-tuning them to use Question-Option-Criteria (QOC): break a task into explicit questions, competing options, and evaluation criteria. Its three-generation pipeline progresses from a basic decision core to richer answer synthesis and statistically enriched reasoning. The reported experiments assess internal consistency and output quality; QOC fine-tuning improves answer quality over non-fine-tuned base models, with especially strong gains when models are large enough to carry out the QOC computations reliably. The abstract presents structured reasoning as a promising alternative to Chain-of-Thought, while providing no specific benchmark results or detailed limitations.

### Source excerpt

arXiv:2611.26282v1 Announce Type: cross Abstract: Reasoning capabilities in large language models have evolved from prompting-based methods to internalized model behaviors. In this paper, we investigate whether the internal thinking model of an LLM can be deliberately changed and whether such a change is beneficial. Instead of relying on Chain-of-Thought, we train models to follow Question--Option--Criteria (QOC), a structured decision process that decomposes a task into explicit questions, competing options, and evaluation criteria. We present a three-generation development pipeline that ranges from a basic QOC decision core to richer answer synthesis and statistically enriched QOC reasoning. We then evaluate the resulting models with respect to both internal consistency and output quality. Across the reported experiments, QOC-based fine-tuning improves answer quality relative to non-fine-tuned base models and yields particularly strong gains once models are large enough to execute the underlying QOC computations reliably. The results suggest that the internal thinking model of an LLM is trainable and that structured alternatives to Chain-of-Thought can provide a promising path toward more reliable, interpretable, and task-adapted decision support.

## Learning to Defer under Expert Drift

DevFeed: [Learning to Defer under Expert Drift](<https://devfeed.tech/articles/learning-to-defer-under-expert-drift-145181.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26440>)

Author: Ziyao Mou, Andrea Wynn, Eric Nalisnick

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [annotation](<https://devfeed.tech/tags/annotation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [aviation](<https://devfeed.tech/tags/aviation.md>), [classification](<https://devfeed.tech/tags/classification.md>), [code](<https://devfeed.tech/tags/code.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [defer](<https://devfeed.tech/tags/defer.md>), [detection](<https://devfeed.tech/tags/detection.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [drift](<https://devfeed.tech/tags/drift.md>), [eda](<https://devfeed.tech/tags/eda.md>), [effective](<https://devfeed.tech/tags/effective.md>), [effectively](<https://devfeed.tech/tags/effectively.md>), [everyday](<https://devfeed.tech/tags/everyday.md>), [learning](<https://devfeed.tech/tags/learning.md>)

### AI overview

EDA-L2D adapts learning-to-defer policies to changing human-expert reliability by conditioning the deferral head on recent expert outcomes through a sequence model. The paper evaluates it on image classification, medical diagnosis, and hate speech detection, including generalization under realistic deferral conditions and irregular reliability shifts. The authors report that it adapts more effectively than prior L2D methods across diverse temporal patterns, improving system performance and deferral decisions. The supplied text does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2611.26440v1 Announce Type: new Abstract: The learning to defer (L2D) framework enables safety in machine learning and AI systems by allocating difficult or critical decisions to a human expert. However, most prior work on L2D assumes fixed expert reliability, overlooking temporal fluctuations in human performance due to factors such as fatigue and cognitive biases. Humans commonly exhibit such substantial, systematic performance shifts across a wide range of domains, from high-stakes settings such as radiology, aviation, and judicial decision-making, to everyday tasks such as crowdsourced image annotation. We propose Expert-Drift-Adapted Learning-to-Defer (EDA-L2D), a novel expert-aware L2D framework that explicitly models these temporal shifts by conditioning the deferral head on recent histories of expert outcomes via a sequence model. This history-aware approach enables adaptive deferral policies that anticipate reliability fluctuations and better allocate decisions between human and machine over time. We provide comprehensive experiments across three diverse tasks -- image classification, medical diagnosis, and hate speech detection -- including generalization analyses under realistic deferral conditions and irregular shifts in expert reliability. Our results show that EDA-L2D adapts more effectively than prior L2D methods to diverse temporal patterns of expert reliability, resulting in improved system performance and more effective deferral decisions. Code is available at https://github.com/ZiyaoMou/L2D-Expert-Drift.

## MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound

DevFeed: [MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound](<https://devfeed.tech/articles/mist-reliable-streaming-decision-trees-for-online-class-incremental-learning-via-mcdiarmid-bound-143260.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.11617>)

Author: Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy, Dao Sy Duy Minh, Huynh Trung Kiet, Long Tran-Thanh

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [continual-learning](<https://devfeed.tech/tags/continual-learning.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [decision-trees](<https://devfeed.tech/tags/decision-trees.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [independent](<https://devfeed.tech/tags/independent.md>), [kll](<https://devfeed.tech/tags/kll.md>), [knowledge-transfer](<https://devfeed.tech/tags/knowledge-transfer.md>), [learning](<https://devfeed.tech/tags/learning.md>), [math-st](<https://devfeed.tech/tags/math-st.md>), [online](<https://devfeed.tech/tags/online.md>), [quantile](<https://devfeed.tech/tags/quantile.md>), [robust](<https://devfeed.tech/tags/robust.md>), [stat-th](<https://devfeed.tech/tags/stat-th.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

MIST addresses two failures of streaming decision trees in online class-incremental learning: split reliability degrades as class count grows, and splitting lacks knowledge transfer. It combines a class-count-independent McDiarmid confidence radius for Gini splits, Bayesian inheritance of parent statistics through truncated-Gaussian moments, and per-leaf KLL sketches for threshold evaluation and geometry-adaptive prediction. The abstract reports competitiveness with global parametric methods on near-Gaussian tabular benchmarks and robustness on non-Gaussian stress tests where leading benchmarks collapse; it provides no quantitative results in the supplied text.

### Source excerpt

arXiv:2605.11617v3 Announce Type: replace Abstract: Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite these, they still fail in online class-incremental learning due to two coupled miscalibrations: (i) their split criterion grows unreliable as the class count K expands, and (ii) the absence of knowledge transfer at split time. Both failures share a common root: the range of Information Gain intrinsically scales with log2 K. Consequently, any Hoeffding-style confidence radius derived from it must inevitably grow with the class count, making a K-independent split criterion structurally impossible, taking away the potential benefits of applying streaming decision trees to continual learning. To fix this issue, we present MIST (McDiarmid Incremental Streaming Tree), which resolves both failures through three integrated components: (i) a tight, K-independent McDiarmid confidence radius for Gini splitting that acts as a structural regulariser; (ii) a Bayesian inheritance protocol that projects parent statistics to child nodes via truncated-Gaussian moments, with variance reduction guarantees strongest precisely when splitting is most conservative; and (iii) per-leaf KLL quantile sketches that support both continuous threshold evaluation and geometry-adaptive leaf prediction from a single data structure. On standard and stress-test tabular streams, MIST is competitive with global parametric methods on near-Gaussian benchmarks and uniquely robust on non-Gaussian geometry where SOTA benchmarks collapse.

## When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

DevFeed: [When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters](<https://devfeed.tech/articles/when-do-foundation-models-pay-off-a-break-even-analysis-of-pretrained-time-series-forecasters-143286.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.04919>)

Author: Nicholas Tan Jerome, Frank Simon

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [lora](<https://devfeed.tech/topics/lora.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [arima](<https://devfeed.tech/tags/arima.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision](<https://devfeed.tech/tags/decision.md>), [ets](<https://devfeed.tech/tags/ets.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [fm](<https://devfeed.tech/tags/fm.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-infrastructure](<https://devfeed.tech/tags/gpu-infrastructure.md>), [history](<https://devfeed.tech/tags/history.md>), [models](<https://devfeed.tech/tags/models.md>), [series](<https://devfeed.tech/tags/series.md>), [time](<https://devfeed.tech/tags/time.md>), [time-series](<https://devfeed.tech/tags/time-series.md>)

### AI overview

Across 30 datasets, zero-shot and LoRA-tuned time-series foundation models beat classical baselines at every tested training fraction on 16 datasets, while classical methods reached break-even with as little as 21-6,324 samples on six others and 24-22,177 on eight. No classical method dominated. For datasets with fewer than 700 training points and non-negligible seasonality, the study recommends zero-shot forecasting and skipping fine-tuning: at under 20% of history, classical methods lost on four of ten such datasets and could not be fitted on six. LoRA rarely helped and degraded short-series performance by up to 52%. The proposed process checks dataset length and seasonality, then uses a brief 5-10% pilot when needed; at this benchmark scale, simple dataset features did not predict break-even outside the short-seasonal-series rule.

### Source excerpt

arXiv:2607.04919v2 Announce Type: replace Abstract: Deploying a time series foundation model (FM) requires GPU infrastructure and engineering overhead, with no guarantee of improvement over classical forecasting methods. We provide the first systematic break-even analysis of when this investment pays off. Across 30 benchmark datasets, we compare zero-shot and LoRA fine-tuned FMs (Chronos-Bolt, Moirai, Lag-Llama) against classical baselines (Naive, ETS, ARIMA, XGBoost) at six training set sizes from 2% to 100% of available data. FMs outperform classical methods at every evaluated training fraction on 16 of 30 datasets. On 6 datasets, classical methods surpass zero-shot FMs with at most 5% of the training data (21--6,324 samples); on the remaining 8, break-even ranges from 24 to 22,177 samples. No classical method dominates: ARIMA, Naive, ETS and XGBoost are each best on 6--11 datasets. One robust rule requires no model training: if n_train < 700 and seasonality is non-negligible, FM zero-shot is the right low-data choice -- below 20% of the history, classical methods either lose to it (4 of these 10 datasets) or cannot be fitted at all (6) -- and it stays best at full history on 6 of them; fine-tuning should be skipped. Contrary to common practice, LoRA fine-tuning rarely helps and degrades short series by up to 52%. We operationalise these findings as a two-step decision framework -- compute dataset length and seasonality strength, run a brief 5--10% pilot only if needed. Cheap dataset features do not predict the break-even category at this benchmark scale, so outside the rule a pilot remains necessary. Code and benchmark: https://github.com/nicolaisi/fm_breakeven.

## Artificial Intelligence in Finance and the Early-Career Skills Shift: A Structured Evidence Synthesis of Decision Delegation, Bank Deployments, and Business Education

DevFeed: [Artificial Intelligence in Finance and the Early-Career Skills Shift: A Structured Evidence Synthesis of Decision Delegation, Bank Deployments, and Business Education](<https://devfeed.tech/articles/artificial-intelligence-in-finance-and-the-early-career-skills-shift-a-structured-evidence-synthesis-of-decision-delegation-bank-deployments-and-business-education-142138.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23261>)

Author: Prakhar Singh Sisodia

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [Trustworthy AI](<https://devfeed.tech/topics/trustworthy-ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [2026](<https://devfeed.tech/tags/2026.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [accountability](<https://devfeed.tech/tags/accountability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [bank](<https://devfeed.tech/tags/bank.md>), [business](<https://devfeed.tech/tags/business.md>), [career](<https://devfeed.tech/tags/career.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [decision](<https://devfeed.tech/tags/decision.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [education](<https://devfeed.tech/tags/education.md>), [finance](<https://devfeed.tech/tags/finance.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [shift](<https://devfeed.tech/tags/shift.md>), [skills](<https://devfeed.tech/tags/skills.md>), [structured](<https://devfeed.tech/tags/structured.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>)

### AI overview

The abstract's central finding is that financial AI is strongest at retrieval, transformation, coding, and first-pass analysis, while delegation should be constrained by consequences, reversibility, verification strength, and operational resilience. Banks are adopting AI for tasks including research, customer service, fraud detection, and multi-step workflows, but the paper argues that productivity gains can weaken early-career apprenticeship if assisted output improves faster than unaided skill. It proposes frameworks for deciding what to delegate and preserving human capability, accountability, and the future talent pipeline. This overview is based on the supplied abstract.

### Source excerpt

arXiv:2611.23261v1 Announce Type: new Abstract: Artificial intelligence is becoming a general interaction and decision-support layer across finance. Banks use AI for research retrieval, document synthesis, meeting follow-up, customer service, coding, fraud detection, risk support, and increasingly multi-step workflows. This paper asks which parts of finance work can be delegated safely, which remain human-owned, and how education should change when AI compresses the tasks through which novices traditionally build judgment. It presents a structured evidence synthesis of research and public evidence released from 2023 through October 2026 across finance, labor economics, education, bank deployments, and financial regulation. Numerical results and deployment claims remain attributed to their original sources. Four connections emerge: AI is strongest at retrieval, transformation, coding, and first-pass analysis; financial institutions are moving toward constrained rather than unrestricted autonomy; productivity assistance can weaken apprenticeship when assisted output improves faster than unaided capability; and delegation should depend jointly on consequence, reversibility, verification strength, and operational resilience. The paper develops a Finance Work Stack, Decision Delegation Matrix, AI Apprenticeship Paradox, Apprenticeship Preservation Protocol, and Career Readiness Stack. It argues that useful financial AI must improve productivity without weakening accountability, human capability, cyber resilience, or the future talent pipeline.

## AI Adoption Maturity Matrix (AAMM): The 5 Levels Every Organization Goes Through

DevFeed: [AI Adoption Maturity Matrix (AAMM): The 5 Levels Every Organization Goes Through](<https://devfeed.tech/articles/ai-adoption-maturity-matrix-aamm-the-5-levels-every-organization-goes-through-140886.md>)

Original publisher: [Read original article](<https://hackernoon.com/ai-adoption-maturity-matrix-aamm-the-5-levels-every-organization-goes-through?source=rss>)

Author: Andre

Published: 2026-11-18T15:48:47Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-adoption-maturity-matrix](<https://devfeed.tech/tags/ai-adoption-maturity-matrix.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-implementation-strategy](<https://devfeed.tech/tags/ai-implementation-strategy.md>), [ai-maturity](<https://devfeed.tech/tags/ai-maturity.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [ai-product-management](<https://devfeed.tech/tags/ai-product-management.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [ai-transformation](<https://devfeed.tech/tags/ai-transformation.md>), [api](<https://devfeed.tech/tags/api.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [board](<https://devfeed.tech/tags/board.md>), [brand](<https://devfeed.tech/tags/brand.md>), [calendar](<https://devfeed.tech/tags/calendar.md>), [checkpoint](<https://devfeed.tech/tags/checkpoint.md>), [classification](<https://devfeed.tech/tags/classification.md>), [claude](<https://devfeed.tech/tags/claude.md>), [company](<https://devfeed.tech/tags/company.md>), [control](<https://devfeed.tech/tags/control.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [maturity](<https://devfeed.tech/tags/maturity.md>), [organization](<https://devfeed.tech/tags/organization.md>)

### AI overview

The AI Adoption Maturity Matrix (AAMM) assesses AI maturity by workflow changes and measured outcomes, not tool access or successful demos. It describes five ordered levels: experimentation and pilots; workflow redesign that separates human judgment from mechanical work; governance with named owners and logged stop criteria; and measured production operation that uses results to improve the workflow. The text calls workflow redesign the commonly skipped step and says to assess each workflow separately, recording the highest level supported by evidence and the gaps below it. Level 5 retains human controls; it does not mean unsupervised operation. Its reported 96% reduction in human workflow hours applies to one marketing workflow and counts only work handled on the platform, about a third of the benchmark; the remaining time is excluded from the claim.

### Source excerpt

A short self-assessment for leaders who want an honest read on where their AI adoption stands today, and a clear idea of what to build next.

## System One Models and the Future of AI Decision-Making

DevFeed: [System One Models and the Future of AI Decision-Making](<https://devfeed.tech/articles/system-one-models-and-the-future-of-ai-decision-making-140479.md>)

Original publisher: [Read original article](<https://hackernoon.com/system-one-models-and-the-future-of-ai-decision-making?source=rss>)

Author: Zafar Iqbal

Published: 2026-11-18T07:30:02Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-routing](<https://devfeed.tech/tags/ai-agent-routing.md>), [ai-decision-making](<https://devfeed.tech/tags/ai-decision-making.md>), [ai-decision-models](<https://devfeed.tech/tags/ai-decision-models.md>), [classification](<https://devfeed.tech/tags/classification.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [costs](<https://devfeed.tech/tags/costs.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [future-of-ai](<https://devfeed.tech/tags/future-of-ai.md>), [generative](<https://devfeed.tech/tags/generative.md>), [jev](<https://devfeed.tech/tags/jev.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm-classification](<https://devfeed.tech/tags/llm-classification.md>), [models](<https://devfeed.tech/tags/models.md>), [routing](<https://devfeed.tech/tags/routing.md>), [structured-outputs](<https://devfeed.tech/tags/structured-outputs.md>), [system-one](<https://devfeed.tech/tags/system-one.md>), [system-one-models](<https://devfeed.tech/tags/system-one-models.md>), [typed-ai-outputs](<https://devfeed.tech/tags/typed-ai-outputs.md>), [typesafe-ai](<https://devfeed.tech/tags/typesafe-ai.md>)

### AI overview

The article argues that software automation is held back by prose based model interfaces: classification decisions require parsing, validation, retries, and confidence estimates that may not be reliable. TypeSafe AI's Jev is presented as a System One alternative that returns predefined typed decisions with probabilities, which the article says avoids string parsing and enables routing uncertain cases to humans. It reports lower latency and cost than generative models on decision tasks, while noting that vendor performance and parity figures are task specific and should be checked on a workload; independent examples cited show smaller but still substantial savings. The proposed division of labor keeps generative models for open ended reasoning and writing, and uses typed decision models at points such as routing or action checks. These comparisons and claims come from the supplied article excerpt.

### Source excerpt

Explore how typed AI decision models like Jev approach classification, agent routing, latency, costs, and confidence compared with generative LLMs.

## OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making

DevFeed: [OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making](<https://devfeed.tech/articles/oicycle-observe-infer-and-intervene-cycle-for-belief-state-learning-in-longitudinal-clinical-decision-making-140083.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22826>)

Author: Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [electronic-health-records](<https://devfeed.tech/tags/electronic-health-records.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [health](<https://devfeed.tech/tags/health.md>), [history](<https://devfeed.tech/tags/history.md>), [hospital](<https://devfeed.tech/tags/hospital.md>), [intervene](<https://devfeed.tech/tags/intervene.md>), [irregular](<https://devfeed.tech/tags/irregular.md>), [laboratory](<https://devfeed.tech/tags/laboratory.md>), [learning](<https://devfeed.tech/tags/learning.md>), [markov](<https://devfeed.tech/tags/markov.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [next](<https://devfeed.tech/tags/next.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

OICycle learns a stochastic Gaussian belief state from longitudinal clinical episodes, updating it by combining a sample of the prior belief with new multimodal observations and the intervention that produced them. It is trained to predict the next clinician intervention, time to the next episode, and next-episode mortality. On a benchmark of 72,075 admissions drawn from MIMIC-IV, MIMIC-IV-Note, and MIMIC-CXR, it outperformed an otherwise identical history-free model on adaptive recall for next intervention (0.347 vs. 0.253), macro-F1 for time to next episode (0.351 vs. 0.293), and macro-F1 for next-episode mortality (0.649 vs. 0.585). The reported benefit of history is concentrated in interventions whose ordering depends on prior findings.

### Source excerpt

arXiv:2611.22826v1 Announce Type: new Abstract: Clinical care is a closed loop: clinicians observe partial evidence, infer the patient's state, and intervene, and each intervention determines what is observed next. This makes clinical decision making a partially observable Markov decision process (POMDP), in which a belief over a latent patient state must be updated from irregular, multimodal, and incomplete records. Yet most deep clinical models predict from a single snapshot or from coarsely aggregated history, while POMDP-based clinical methods need hand-specified discrete state spaces and transition models that real electronic health records cannot supply. We introduce OICycle (Observe, Infer, and Intervene Cycle), which learns a stochastic belief state directly from retrospective trajectories. At every episode, a learned recurrent operator fuses a sample of the previous belief with the new multimodal observations and the intervention that produced them. The resulting Gaussian belief is trained to predict clinicians' next interventions, the time to the next episode, and next-episode mortality. To enable reproducible evaluation, we release a benchmark derived from MIMIC-IV, MIMIC-IV-Note, and MIMIC-CXR that organizes 72,075 hospital admissions (5.4M laboratory, microbiology, radiology, prescription, and note records) into temporally ordered therapeutic--diagnostic episodes. Compared with an otherwise identical history-free model, OICycle improves next-intervention adaptive recall from 0.253 to 0.347, time-to-next-episode macro-F1 from 0.293 to 0.351, and next-episode mortality macro-F1 from 0.585 to 0.649. Analysis shows that the learned belief encodes intervention type and trajectory position and evolves smoothly across episodes, and that the benefit of history is concentrated in interventions whose ordering depends on prior findings.

## When Do Typed Decision Models Work in Transportation? Evidence from Travel Choice and Traffic Signal Control

DevFeed: [When Do Typed Decision Models Work in Transportation? Evidence from Travel Choice and Traffic Signal Control](<https://devfeed.tech/articles/when-do-typed-decision-models-work-in-transportation-evidence-from-travel-choice-and-traffic-signal-control-140094.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22926>)

Author: Hongyang Zhang, Boyuan Deng, Siyuan Feng, Kai Chen, Junbo Zhang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [choice](<https://devfeed.tech/tags/choice.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [inference](<https://devfeed.tech/tags/inference.md>), [input](<https://devfeed.tech/tags/input.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [latency](<https://devfeed.tech/tags/latency.md>), [learning-algorithms](<https://devfeed.tech/tags/learning-algorithms.md>), [models](<https://devfeed.tech/tags/models.md>), [signal](<https://devfeed.tech/tags/signal.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [transportation](<https://devfeed.tech/tags/transportation.md>), [travel](<https://devfeed.tech/tags/travel.md>)

### AI overview

Typed decision models return a chosen action and option-level probabilities with lower inference latency and computational cost than the evaluated chat-based language models. In Swissmetro travel-mode prediction, TypeSafe Jev and GPT-6 Luna Decisions are less accurate than traditional discrete choice models and the strongest chat-based baseline, and results vary with input representation and question framing. In closed-loop traffic signal control, they perform competitively with established controllers in some scenarios but degrade under more challenging network conditions. The findings suggest potential for efficient zero-shot decisions with predefined alternatives, while highlighting sensitivity to task conditions and input design.

### Source excerpt

arXiv:2611.22926v1 Announce Type: cross Abstract: Typed decision models combine natural-language understanding with a structured interface that returns a selected action and an option-level probability distribution without generating lengthy textual responses. Their low inference cost and response latency make them attractive for transportation problems with predefined alternatives. This paper investigates their effectiveness, robustness, and efficiency in two representative transportation tasks: individual travel-mode choice prediction and sequential traffic signal control. We systematically evaluate TypeSafe Jev and GPT-6 Luna Decisions against conventional transportation methods, reinforcement learning algorithms, and four chat-based large language models. Experiments on the Swissmetro dataset show that typed decision models achieve lower prediction accuracy than traditional discrete choice models and the strongest chat-based baseline, while their performance varies substantially with input representation and question framing. In closed-loop traffic signal control experiments, typed decision models demonstrate competitive performance against established controllers in several scenarios, but exhibit performance degradation under more challenging network conditions. Furthermore, the typed models achieve lower inference latency and computational cost than the evaluated chat-based large language models, highlighting their potential for efficient, zero-shot transportation decision-making. Overall, these findings demonstrate both the potential and limitations of typed decision models, emphasizing the importance of input design, task characteristics, and robustness evaluation for their effective application in transportation systems.

## Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information

DevFeed: [Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information](<https://devfeed.tech/articles/remembered-as-brief-stored-preferences-silentlyremove-decision-critical-information-140068.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22697>)

Author: Joshua Adrian Cahyono

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Stateful](<https://devfeed.tech/topics/stateful.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [health](<https://devfeed.tech/tags/health.md>), [memory](<https://devfeed.tech/tags/memory.md>), [warning](<https://devfeed.tech/tags/warning.md>)

### AI overview

The benchmark finds that stored user preferences can silently remove decision-critical information and influence choices. Across 100 decisions in 25 domains and five models, Gemini 2.5 Flash-Lite and DeepSeek V4 Pro saved a web page's planted request for very short answers without warnings as the user's preference in every episode. Later answers missed a critical item in 93% and 84% of cases, usually silently; with a stated brevity preference, 78-96% of omissions were silent. The same models chose for users in 80% and 95% of value-dependent choices, compared with none under neutral memory. A one-line instruction reduced silent gaps to 2-8% but left most missing content unaddressed. Listing must-know points before applying the user profile restored more content in four of five models.

### Source excerpt

arXiv:2611.22697v1 Announce Type: new Abstract: People increasingly learn what they need for decisions about health, money, law and safety from AI assistants, and what an assistant leaves out the user never sees. An answer with a warning removed can be true in every sentence, so fact-checks pass it, and an assistant with memory applies a preference stored once to later questions the user never had in mind. We introduce \bench{}, an Inspect benchmark of 100 everyday decisions across 25 domains in which only the assistant's memory of the user varies: the user states a belief, the model infers it from a remark, or a web page the user asked to summarise plants it. Testing five models, we find three effects. First, after summarising a page with one line addressed to AI assistants, Gemini 2.5 Flash-Lite and DeepSeek V4 Pro save ``prefers very short answers and does not want warnings'' as the user's preference in every episode, and 93\% and 84\% of their later answers miss a critical item, almost always silently; under a stated brevity preference, 78--96\% of omissions are silent. Second, the same two models then pick an option for the user on 80\% and 95\% of value-dependent choices, against none with neutral memory. Third, a one-line instruction leaves 2--8\% of answers with a silent gap but most missing content still missing, while listing the must-know points before applying the user profile restores more of the content in four of five models. We release the scenarios, harness and logs.

## Evaluating Semantic Insensitivity in Financial Sentiment Analysis: Implications for Sustainable Financial Decision-Making

DevFeed: [Evaluating Semantic Insensitivity in Financial Sentiment Analysis: Implications for Sustainable Financial Decision-Making](<https://devfeed.tech/articles/evaluating-semantic-insensitivity-in-financial-sentiment-analysis-implications-for-sustainable-financial-decision-making-139891.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21653>)

Author: Gabriela Cioboata, Teodor-Stefan Bildea

Published: 2026-11-18T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [asi](<https://devfeed.tech/tags/asi.md>), [attack](<https://devfeed.tech/tags/attack.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [features](<https://devfeed.tech/tags/features.md>), [financial](<https://devfeed.tech/tags/financial.md>), [framework](<https://devfeed.tech/tags/framework.md>), [lexical](<https://devfeed.tech/tags/lexical.md>), [llm](<https://devfeed.tech/tags/llm.md>), [logic](<https://devfeed.tech/tags/logic.md>), [logical](<https://devfeed.tech/tags/logical.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [models](<https://devfeed.tech/tags/models.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [robust](<https://devfeed.tech/tags/robust.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [sentiment-analysis](<https://devfeed.tech/tags/sentiment-analysis.md>)

### AI overview

The Agent-driven Semantic Inversion (ASI) framework uses an LLM-powered multi-agent pipeline to select eligible financial news sentences and apply targeted lexical substitutions that invert financial meaning. In evaluation, it deceived FinBERT in 90.85% of eligible cases; the model often kept its original sentiment prediction despite the inversion of financial performance indicators. The authors' qualitative and token-level analyses suggest FinBERT relies heavily on contextual keywords and syntax rather than logical comprehension of financial semantics. The abstract argues for more logic-aware, robust financial NLP models to improve the reliability of automated decisions.

### Source excerpt

arXiv:2611.21653v1 Announce Type: cross Abstract: Financial sentiment analysis is critical for automated trading, portfolio management, and risk assessment, heavily relying on models like FinBERT. Despite high benchmark accuracy, these models remain vulnerable to subtle adversarial text modifications, threatening the integrity of algorithmic decision-making. In this paper, we propose Agent-driven Semantic Inversion (ASI), a novel adversarial attack framework targeting financial sentiment models through domain-specific semantic manipulation. Utilizing an LLM-powered multi-agent pipeline, our approach identifies eligible financial news sentences and applies targeted lexical substitutions. We empirically evaluate ASI against FinBERT, one of the most widely deployed financial sentiment models. Our results reveal a striking vulnerability: the attack successfully deceived FinBERT in 90.85% of eligible cases, with the model frequently maintaining its original sentiment prediction despite the fundamental inversion of financial performance indicators. Through qualitative analysis and token-level investigation, we demonstrate that FinBERT critically over-relies on contextual keywords and syntactic patterns rather than true logical comprehension of financial semantics. Our findings highlight the urgent need for logic-aware, robust financial NLP models to ensure the reliability of automated decision-making systems.

## Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining

DevFeed: [Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining](<https://devfeed.tech/articles/exploring-explainable-multi-agent-mcts-minimax-hybrids-in-board-game-using-process-mining-139740.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2503.23326>)

Author: Yiyu Qian, Tim Miller, Liyuan Zhao

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [monte carlo tree search](<https://devfeed.tech/topics/monte-carlo-tree-search.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [board-game](<https://devfeed.tech/topics/board-game.md>)

Tags: [board-game](<https://devfeed.tech/tags/board-game.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [minimax](<https://devfeed.tech/tags/minimax.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [process-mining](<https://devfeed.tech/tags/process-mining.md>)

### AI overview

The paper investigates explaining agents' strategies in 3v3 checkers by applying process mining to multi-agent Monte-Carlo Tree Search (MCTS). It addresses MCTS's selective search, which can miss crucial moves and fall into tactical traps, by integrating shallow full-width minimax search into the rollout phase. The supplied abstract describes this as ongoing work and gives no results comparing performance or explanations.

### Source excerpt

arXiv:2503.23326v4 Announce Type: replace Abstract: Monte-Carlo Tree Search (MCTS) is a family of sampling-based search algorithms widely used for online planning in sequential decision-making domains and at the heart of many recent advances in artificial intelligence. Understanding the behavior of MCTS agents is difficult for developers and users due to the frequently large and complex search trees that result from the simulation of many possible futures, their evaluations, and their relationships. This paper presents our ongoing investigation into potential explanations for the decision-making and behavior of MCTS. A weakness of MCTS is that it constructs a highly selective tree and, as a result, can miss crucial moves and fall into tactical traps. Full-width minimax search constitutes the solution. We integrate shallow minimax search into the rollout phase of multi-agent MCTS and use process mining technique to explain agents' strategies in 3v3 checkers.

## Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection

DevFeed: [Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection](<https://devfeed.tech/articles/decision-aware-proximal-bridge-learning-for-optimal-treatment-selection-141561.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.16989>)

Author: Tom\\\`as Garriga, Alejandro Almod\\'ovar, Axel Brando, Gerard Sanz, Eduard Serrahima de Cambra, Juan Parras

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [causal-inference](<https://devfeed.tech/tags/causal-inference.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [effect](<https://devfeed.tech/tags/effect.md>), [global](<https://devfeed.tech/tags/global.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [inference](<https://devfeed.tech/tags/inference.md>), [learning](<https://devfeed.tech/tags/learning.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [policy](<https://devfeed.tech/tags/policy.md>), [projection](<https://devfeed.tech/tags/projection.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [proxy-variables](<https://devfeed.tech/tags/proxy-variables.md>), [regions](<https://devfeed.tech/tags/regions.md>), [response](<https://devfeed.tech/tags/response.md>), [selection](<https://devfeed.tech/tags/selection.md>)

### AI overview

For continuous treatment selection under hidden confounding, estimating a causal response surface uniformly can misallocate effort away from treatments that determine the best decision. The paper proposes a policy-targeted weighted bridge loss for proximal causal inference, emphasizing decision-relevant treatment regions while retaining global stabilization. A regret bound links treatment-selection regret to a weighted ill-posedness constant. Decision-aware versions of several proximal bridge solvers alternate weighted bridge estimation, response-surface projection, policy updates, and weight refinement. The abstract reports reduced regret across several bridge solvers; identification relies on proxy variables and bridge functions under suitable assumptions.

### Source excerpt

arXiv:2605.16989v2 Announce Type: replace Abstract: Individualized treatment selection with continuous actions requires accurate causal response estimation in decision-relevant regions, rather than uniformly over the entire action space. Estimating a global causal response surface and then choosing the treatment that maximizes it can therefore be suboptimal, since standard estimation objectives allocate modeling effort according to the observed treatment distribution rather than the regions that determine the optimal decision. While decision-aware approaches have been studied in unconfounded settings, this problem remains underexplored in proximal causal inference, where proxy variables and bridge functions enable identification under suitable assumptions even in the presence of hidden confounding. Despite recent progress, proximal methods have primarily focused on treatment-effect and potential-outcome estimation rather than treatment selection and optimal decision-making. To bridge this gap, we introduce a policy-targeted weighted bridge loss that emphasizes decision-relevant treatment regions while retaining global stabilization. We prove a regret bound showing that the proposed weighted bridge loss controls treatment-selection regret through a weighted ill-posedness constant. We instantiate the framework in decision-aware variants of several proximal bridge solvers, yielding practical algorithms that alternate between weighted bridge estimation, response-surface projection, policy update, and weight refinement. Empirically, we find that decision-aware weighting reduces regret across several bridge solvers, suggesting improved treatment selection in proximal settings.

## How to enable smart manufacturing with AI-powered insights | Blog | Fivetran

DevFeed: [How to enable smart manufacturing with AI-powered insights | Blog | Fivetran](<https://devfeed.tech/articles/how-to-enable-smart-manufacturing-with-ai-powered-insights-blog-fivetran-140238.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/how-to-enable-smart-manufacturing-with-ai-powered-insights>)

Author: Fivetran

Published: 2026-11-18T04:00:45Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [smart-manufacturing](<https://devfeed.tech/tags/smart-manufacturing.md>)

### AI overview

Manufacturers can use AI for forecasting and generative tasks, but fragmented data and manual processes hinder adoption. The article describes supply chain command centers as hubs that combine equipment, analytics, automation and business processes to support end-to-end monitoring, disruption alerts, scenario modeling and routine decision automation. Tredence provides data architecture, modernization and AI capabilities; Fivetran supplies automated ingestion from more than 700 sources into analytics platforms. In an aluminum plant example, the partners streamed historian data and ingested batch quality data from edge to cloud, developed predictive models with Databricks and Microsoft Azure, then deployed them at the plant edge. The company reported 23% fewer production stoppages, 17% less work-in-process scrap and about 7% improved product quality.

### Source excerpt

Connect data from across all sources to see, understand, and predict every aspect of manufacturing operations and optimize decision making.

## To Become Data-Driven, Align Talent, Tools and Processes | Blog | Fivetran

DevFeed: [To Become Data-Driven, Align Talent, Tools and Processes | Blog | Fivetran](<https://devfeed.tech/articles/to-become-data-driven-align-talent-tools-and-processes-blog-fivetran-140262.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/to-become-data-driven-align-talent-tools-and-processes>)

Author: Adrian McGill

Published: 2026-11-18T02:45:59Z

Content type: article

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [business-intelligence](<https://devfeed.tech/topics/business-intelligence.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [align](<https://devfeed.tech/tags/align.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automated](<https://devfeed.tech/tags/automated.md>), [bi](<https://devfeed.tech/tags/bi.md>), [bi-tools](<https://devfeed.tech/tags/bi-tools.md>), [blog](<https://devfeed.tech/tags/blog.md>), [braze](<https://devfeed.tech/tags/braze.md>), [business](<https://devfeed.tech/tags/business.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [insights](<https://devfeed.tech/tags/insights.md>), [key](<https://devfeed.tech/tags/key.md>), [processes](<https://devfeed.tech/tags/processes.md>), [resources](<https://devfeed.tech/tags/resources.md>), [strategies](<https://devfeed.tech/tags/strategies.md>), [talent](<https://devfeed.tech/tags/talent.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The article argues that becoming data-driven requires sustained alignment of people, processes, and technology--not just executive support or new tools. It recommends automating integration so analysts can focus on insights; partnering with an influential business stakeholder on a measurable revenue or cost proof of concept who can evangelize data use; presenting clear visual insights that guide action; giving business users one shareable BI tool as a single source of truth; and scaling adoption through business-led training in data analysis, interrogation, and visualization. The excerpt offers these as strategies, without evaluating particular BI tools.

### Source excerpt

Use these five strategies to align key resources and ensure that insights guide your decision-making.

## Liquid AI Releases d1.2 and d1.2-ultra: Omnimodal Decision Models That Top the AA Decision Index

DevFeed: [Liquid AI Releases d1.2 and d1.2-ultra: Omnimodal Decision Models That Top the AA Decision Index](<https://devfeed.tech/articles/liquid-ai-releases-d1-2-and-d1-2-ultra-omnimodal-decision-models-that-top-the-aa-decision-index-137110.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/17/liquid-ai-d1-2-omnimodal-decision-models/>)

Author: Asif Razzaq

Published: 2026-11-17T09:20:57Z

Content type: release

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audio](<https://devfeed.tech/tags/audio.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [images](<https://devfeed.tech/tags/images.md>), [index](<https://devfeed.tech/tags/index.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [liquid-ai](<https://devfeed.tech/tags/liquid-ai.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [releases](<https://devfeed.tech/tags/releases.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [text](<https://devfeed.tech/tags/text.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [zero](<https://devfeed.tech/tags/zero.md>)

### AI overview

Liquid AI's d1.2 family accepts text, images and audio, returning probabilities over fixed answers without generating output tokens. The excerpt reports d1.2-ultra scored 75 on Artificial Analysis Decision Index v2.1, ahead of d1.2 at 69; Liquid AI reports calibration errors of 0.8 and 1.2 points, respectively, across 13 benchmarks, based on its own tests. Five added answer types handle value extraction, span finding, object boxes, ranged estimates and multiple applicable choices. On held-out audio recordings, both models answered 95-97% correctly; d1.2 outperformed ultra on multi-label picks, 90% to 87%. d1.2 is described as faster and less than half the price of ultra. Both are hosted through Liquid's API; weights, parameter counts and latency figures are unavailable in the excerpt.

### Source excerpt

Liquid AI released d1.2 and d1.2-ultra, decision models that read text, images and audio and return calibrated probabilities with zero output tokens. d1.2-ultra scores 75 on the Artificial Analysis Decision Index v2.1. The post Liquid AI Releases d1.2 and d1.2-ultra: Omnimodal Decision Models That Top the AA Decision Index appeared first on MarkTechPost.

## Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis

DevFeed: [Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis](<https://devfeed.tech/articles/vibe-synthesis-hierarchical-agentic-decision-making-for-intent-driven-multistep-molecule-synthesis-137342.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18772>)

Author: Jie Chen, Guikun Chen, Feng Wan, Ning Xu, Wen Liu, Yixiang Ruan, Yiyi Qiu, Haohua Li, Wei Wang, Yi Wang, Xiaoxue Wang, Peng Wang, Jiazhou Zhu, Jun Xuan, Chengxi Li, Jianhong Xu, Wenguan Wang, Yiming M

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [amino-acids](<https://devfeed.tech/tags/amino-acids.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automation](<https://devfeed.tech/tags/automation.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [laboratory](<https://devfeed.tech/tags/laboratory.md>), [laboratory-automation](<https://devfeed.tech/tags/laboratory-automation.md>), [medicine](<https://devfeed.tech/tags/medicine.md>), [physics-chem-ph](<https://devfeed.tech/tags/physics-chem-ph.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [target](<https://devfeed.tech/tags/target.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

VibeSyn uses hierarchical agents to turn chemist-defined molecular goals and accumulating experimental evidence into adaptive synthesis decisions, executed with computational tools and laboratory automation. The authors report three demonstrations, ranging from evidence-grounded experimental decisions to a ten-step total synthesis of catharanthine and synthesis of cyclic peptides containing unnatural amino acids. In the long-horizon campaigns, active human input and simple confirmation represented less than 7.5% and 5.2%, respectively, of recorded workflow actions and outcomes. The supplied text is an abstract and does not provide further methodological or performance details.

### Source excerpt

arXiv:2611.18772v1 Announce Type: cross Abstract: The ability to construct complex molecules underpins advances in medicine and the molecular sciences. Yet long-horizon multistep synthesis requires decisions to be revised as evidence accumulates across chemically dependent operations, a capability not readily supported by artificial-intelligence tools and automated platforms organized around predefined tasks and hard-coded workflows. Here we propose and demonstrate a vibe synthesis system (VibeSyn), an intent-driven architecture in which hierarchical agents translate chemist-defined molecular objectives and accumulating evidence into adaptive decisions executed through computational tools and laboratory automation. We evaluate VibeSyn in three demonstrations of increasing scope and autonomy, progressing from evidence-grounded experimental decisions to adaptive execution of a ten-step total synthesis of catharanthine and structure-to-compound synthesis of cyclic peptides containing unnatural amino acids (uAAs). Across the long-horizon campaigns, active human input and simple confirmation account for less than 7.5% and 5.2%, respectively, of recorded workflow actions and outcomes. VibeSyn points towards a future in which chemists define synthetic intent and agent-directed laboratories autonomously navigate the evolving experimental trajectory required to deliver the target compound.

## AdaMenu: Query-Adaptive Menus for Decision Models over Large Label Spaces

DevFeed: [AdaMenu: Query-Adaptive Menus for Decision Models over Large Label Spaces](<https://devfeed.tech/articles/adamenu-query-adaptive-menus-for-decision-models-over-large-label-spaces-138816.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19005>)

Author: Jiangze Yan, Yi Shen, Jieyun Huang, Wenjing Zhang, Zhaoxiang Liu, Ning Wang, Kai Wang, Shiguo Lian

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [beam-search](<https://devfeed.tech/tags/beam-search.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [error-propagation](<https://devfeed.tech/tags/error-propagation.md>), [limits](<https://devfeed.tech/tags/limits.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [size](<https://devfeed.tech/tags/size.md>), [token-usage](<https://devfeed.tech/tags/token-usage.md>)

### AI overview

AdaMenu handles large classification label sets by retrieving labeled examples to build a query-adaptive candidate menu, then making one decision-model request. Its default setting also adjusts menu size using aggregated retrieval scores. Across four label sets with up to 1,016 labels, it beat TypeSafe's beam-search baseline on all 16 model and label-set pairs where both ran, by 16.6-34.3 percentage points in accuracy. Against the full menu on the three smaller sets, accuracy ranged from 0.5 points lower to 7.2 points higher, while input token use fell by factors of 3.2-22.9. AdaMenu also ran in settings where option limits ruled out the full menu and the hierarchical baseline was unavailable.

### Source excerpt

arXiv:2611.19005v1 Announce Type: new Abstract: Decision models such as Jev return probabilities over caller-defined options and are increasingly used for classification. Large label spaces challenge both accuracy and scalability: larger menus can impair decisions, increase input costs, and exceed option limits. Hierarchical classification reduces menu size but introduces serial calls and error propagation. We propose AdaMenu, which builds a compact candidate menu from retrieved labeled examples and makes a single decision-model request. Its candidate labels adapt to the query, and its default setting also adjusts menu size using aggregated retrieval scores. We evaluate AdaMenu with open and closed decision models on four label sets containing up to 1,016 labels. It outperforms TypeSafe's beam-search baseline on all 16 model and label-set pairs where both methods run, improving accuracy by 16.6-34.3 percentage points. Relative to the full menu on the three smaller label sets, accuracy differences range from -0.5 to +7.2 percentage points, while input token usage falls by factors of 3.2-22.9. AdaMenu also runs when option limits exclude the full menu, including settings where the hierarchical baseline is unavailable.

## When the Cheapest Feasible Router Fails: Auditing Deployment Commitments in Cost-Aware LLM Routing

DevFeed: [When the Cheapest Feasible Router Fails: Auditing Deployment Commitments in Cost-Aware LLM Routing](<https://devfeed.tech/articles/when-the-cheapest-feasible-router-fails-auditing-deployment-commitments-in-cost-aware-llm-routing-139046.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20417>)

Author: Minxuan Hu, Qishi Zhan, Ziheng Chen, Zhengtao Yao, Zihan Dong, Jiayu Yi, Wenxi Sun

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [audit](<https://devfeed.tech/topics/audit.md>)

Tags: [22](<https://devfeed.tech/tags/22.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [control](<https://devfeed.tech/tags/control.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [failure](<https://devfeed.tech/tags/failure.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [nested](<https://devfeed.tech/tags/nested.md>), [operational](<https://devfeed.tech/tags/operational.md>), [policies](<https://devfeed.tech/tags/policies.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [risk](<https://devfeed.tech/tags/risk.md>), [router](<https://devfeed.tech/tags/router.md>), [routing](<https://devfeed.tech/tags/routing.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [service](<https://devfeed.tech/tags/service.md>), [serving](<https://devfeed.tech/tags/serving.md>)

### AI overview

Across 19 RouterBench task families, the cheapest router that passed an empirical audit violated the held-out service contract in 32.22% of its deployments, despite deploying in 91.82% of opportunities. The study treats deployment as a separate commitment decision using disjoint construction, audit, and test samples. Its Menu-Aware Routing Commitment (MARC) uses audit evidence and a serving-cost tolerance to keep the apparent winner, choose a supported alternative, or defer. The policywise variant MARC-P reduced observed conditional failure to 0.73% while deploying in 85.79% of opportunities, at higher serving cost. Fixed-margin and formal risk-control procedures were competitive alternatives. Nested audits and learned semantic routing showed related effects. These findings are reported in the supplied abstract.

### Source excerpt

arXiv:2611.20417v1 Announce Type: new Abstract: Cost-aware LLM routing often selects the cheapest policy meeting empirical risk and coverage constraints. Yet a router that passes an audit can violate its fixed service contract on new requests, even when candidate policies are constructed independently. We study this deployment-commitment decision with disjoint construction, audit, and test samples. Across 19 RouterBench task families, the cheapest audit-feasible router deploys in 91.82% of opportunities but violates the held-out contract in 32.22% of deployments. We introduce Menu-Aware Routing Commitment (MARC), which qualifies policies using audit evidence and a serving-cost tolerance to retain the apparent winner, deploy a supported alternative, or defer. Its practical policywise variant (MARC-P) reduces observed conditional failure to 0.73% at 85.79% deployment, with higher serving cost; fixed-margin and formal risk-control procedures provide competitive alternatives. Nested audits show how added evidence changes deployable policy sets, and learned semantic routing exhibits the same commitment failure. These results establish deployment commitment as a distinct operational decision connecting router evaluation, service reliability, and inference cost.

## Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making

DevFeed: [Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making](<https://devfeed.tech/articles/tensorized-automata-algebraically-informed-representation-learning-for-sequential-decision-making-139181.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21514>)

Author: Anand Balakrishnan, Dweep Trivedi, Swarat Chaudhuri

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [boolean](<https://devfeed.tech/tags/boolean.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [execution](<https://devfeed.tech/tags/execution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [formal](<https://devfeed.tech/tags/formal.md>), [language](<https://devfeed.tech/tags/language.md>), [learning](<https://devfeed.tech/tags/learning.md>), [policy](<https://devfeed.tech/tags/policy.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [results](<https://devfeed.tech/tags/results.md>), [sequential-decision](<https://devfeed.tech/tags/sequential-decision.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

The paper presents a pipeline that uses alternating finite automata to represent both task objectives and progress: AND-OR message passing learns task and state vectors, and selected configurations define an event-driven Boolean matrix operator. The authors prove that language coverage at the start and after each transition lets the operator's carrier encode the exact residual language, with a capacity bound based on reachable configurations; the same pipeline handles conjunction and disjunction. In XLand experiments, pooled execution-state vectors outperform raw carrier bits and task-blind conditioning across three task pools and two rejection rewards, reaching 77.3% success on multi-event tasks and 99.4% on a four-task stratum using 16 operator slots. LetterWorld results indicate useful residual conditioning but retain a gap to RAD. The evidence is an abstract and does not establish broader performance beyond the reported experiments.

### Source excerpt

arXiv:2611.21514v1 Announce Type: cross Abstract: Task representations for sequential decision making should describe both an objective and progress toward it. We present an algebraically informed pipeline that uses the relational structure and language semantics of alternating finite automata (AFAs) to learn control features and compile compact execution operators. AND-OR message passing learns task and state vectors; selected configurations define an event-driven Boolean matrix operator. We prove that initial and successor language coverage make its carrier represent the exact residual after every prefix, with a sufficient capacity bound in terms of reachable configurations. Conjunction and disjunction use the same pipeline. Fidelity and composition audits evaluate copied formulas and learned disjunct assignments. In five-policy-seed XLand experiments with larger training pools, pooled execution-state vectors outperform raw carrier bits and task-blind conditioning across three task pools under two rejection rewards. They achieve 77.3\% success on multi-event tasks and 99.4\% on a four-task stratum with 33--128-state minimal DFAs, using 16 operator slots. LetterWorld results show useful residual conditioning alongside a remaining gap to RAD. These results connect algebraically informed representation learning to compact task execution and useful policy conditioning.

## Hilbert States for Decision-Making under Partial Observability

DevFeed: [Hilbert States for Decision-Making under Partial Observability](<https://devfeed.tech/articles/hilbert-states-for-decision-making-under-partial-observability-137637.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20970>)

Author: Zibo Meng, Andrew C. M. Austin, Alin Achim

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [information](<https://devfeed.tech/tags/information.md>), [learning](<https://devfeed.tech/tags/learning.md>), [observability](<https://devfeed.tech/tags/observability.md>), [simulations](<https://devfeed.tech/tags/simulations.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

The paper separates partial observability's irreducible decision loss from representation and learning errors. It characterizes when conflicting conditional action preferences cause regret, including a zero-regret criterion, a positive lower bound under stated cost-gap conditions, and an exact binary-action formula; state ambiguity alone does not necessarily cause loss. For two actions with squared terminal-goal costs in the plane, three conditional moment contrasts yield a goal-conditioned Hilbert state that preserves observation-optimal actions without reconstructing hidden states. Its three-dimensional form is minimal for exact bilinear cost-contrast representations under nondegenerate history and goal variation. The authors also connect finite-data state errors to excess regret through goal-projected errors, action margins, and goal geometry. Simulations and held-out real-SAR experiments support action preservation and feasible decisions from masked images, while evaluations show reliability varies by goal.

### Source excerpt

arXiv:2611.20970v1 Announce Type: new Abstract: Decision-making under partial observability can be fundamentally limited by information, even with known dynamics: distinct physical states can induce the same observation history while favoring different actions. We study three questions: when is full-state optimality unattainable, what information exactly preserves the best observation-based decision, and how does finite-data learning affect reliability? First, we characterize decision ambiguity through conditional action preferences. We give a zero-regret criterion, a positive lower bound for conflicting uniquely optimal actions on positive-probability regions with uniformly positive cost gaps, and an exact binary-action regret formula. This also shows why physical-state ambiguity alone need not cause decision loss. Second, for two actions and squared terminal-goal costs in the plane, we derive an exact inner-product representation of conditional expected cost differences using three conditional moment contrasts and a goal-dependent feature. This Hilbert state preserves observation-optimal actions without hidden-state reconstruction. Under nondegenerate history and goal variation, its three-dimensional form is minimal among exact bilinear cost-contrast representations. Third, we relate finite-data state errors to excess decision regret via goal-projected errors, action margins, and goal geometry. Physics-based simulations verify information-limited regret, exact action preservation, and the role of second moments. Held-out real-SAR experiments demonstrate feasible goal-conditioned decisions from masked images, while finite-data evaluations reveal goal-dependent reliability. Together, these results separate irreducible information loss, exact representation sufficiency, and learning-induced excess regret.

[Next page](<https://devfeed.tech/topics/decision-making.md?cursor=WyIyMDI2LTExLTE3VDA1OjAwOjAwKzAwOjAwIiwgIjMzZDFhNmI4LTU0MDUtNDg3Ny1iMTBlLTdiOGE0MTMwOGYzNSJd>)