# Context-aware AI

AI systems that use contextual information to adapt support, interventions, or responses to users and environments.

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

## UbiHearo: Bringing Scenario-Aware Sound Guidance to DHH Users with Mobile Agents

DevFeed: [UbiHearo: Bringing Scenario-Aware Sound Guidance to DHH Users with Mobile Agents](<https://devfeed.tech/articles/ubihearo-bringing-scenario-aware-sound-guidance-to-dhh-users-with-mobile-agents-137601.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20686>)

Author: Fengmin Wu, Sicong Liu, Zimu Zhou, Chenren Xu, Wanbing Zhao, Peiwen Sun, Zhiwen Yu

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

Content type: article

Language: en

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

Topics: [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [ai-on-mobile](<https://devfeed.tech/topics/ai-on-mobile.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [audio](<https://devfeed.tech/tags/audio.md>), [audio-language-model](<https://devfeed.tech/tags/audio-language-model.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [context](<https://devfeed.tech/tags/context.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [dhh](<https://devfeed.tech/tags/dhh.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [intermediate](<https://devfeed.tech/tags/intermediate.md>), [intermediate-representations](<https://devfeed.tech/tags/intermediate-representations.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [model](<https://devfeed.tech/tags/model.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [processing](<https://devfeed.tech/tags/processing.md>), [sound](<https://devfeed.tech/tags/sound.md>)

### AI overview

UbiHearo aims to help Deaf and Hard-of-Hearing users interpret sounds in context, assess urgency, and decide what to do. Its neuro-symbolic design turns continuous audio and physical context into structured representations for reasoning and guidance. It limits always-on processing to perceptually meaningful events while using deterministic overrides to preserve safety-critical cues. For scenario understanding, an on-device audio-language model uses those representations rather than user-written context prompts. Lightweight on-device updates personalize guidance while retaining population-aligned reasoning. The abstract reports evaluation on smartphones and in-vehicle systems, with favorable accuracy, latency, and energy tradeoffs, but gives no detailed metrics.

### Source excerpt

arXiv:2611.20686v1 Announce Type: new Abstract: For Deaf and Hard-of-Hearing (DHH) users, effective sound awareness goes beyond detecting \emph{what} sound occurs; it requires understanding \emph{what it means}, \emph{how urgent it is}, and \emph{what to do}. However, existing mobile assistants largely reduce acoustic scenes to isolated labels or generic alerts, failing to provide contextual guidance when the same sound implies different risks across scenarios. We present \sysname, a mobile hearing assistant agent that closes the sensing--reasoning--action loop for \textit{scenario-aware} and \textit{personalized} DHH assistance. \sysname adopts a \textit{neuro-symbolic} design that transforms continuous acoustic and physical context streams into structured intermediate representations (IRs) for controllable reasoning and guidance. It introduces three key mechanisms. \textit{First}, a perception-thresholded sensing mechanism enables energy-efficient always-on awareness by activating processing only for perceptually meaningful events while preserving safety-critical cues through deterministic overrides. \textit{Second}, a staged neuro-symbolic reasoning framework performs promptless scenario understanding by conditioning an on-device audio-language model on structured IRs instead of user-authored context descriptions. \textit{Third}, a bounded human-in-the-loop personalization mechanism adapts user-specific guidance through lightweight on-device decision-boundary updates while preserving population-aligned reasoning. We evaluate \sysname on smartphones and in-vehicle systems across diverse scenarios. It achieves favorable accuracy--latency--energy tradeoffs and personalized guidance.

## Contextual Causal Bayesian Optimisation

DevFeed: [Contextual Causal Bayesian Optimisation](<https://devfeed.tech/articles/contextual-causal-bayesian-optimisation-138703.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2301.12412>)

Author: Vahan Arsenyan, Antoine Grosnit, Haitham Bou-Ammar, Arnak Dalalyan

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

Content type: article

Language: en

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

Topics: [causality](<https://devfeed.tech/topics/causality.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [approach](<https://devfeed.tech/tags/approach.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [environments](<https://devfeed.tech/tags/environments.md>), [expectation](<https://devfeed.tech/tags/expectation.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [information](<https://devfeed.tech/tags/information.md>), [novel](<https://devfeed.tech/tags/novel.md>), [optimisation](<https://devfeed.tech/tags/optimisation.md>), [policies](<https://devfeed.tech/tags/policies.md>), [probability](<https://devfeed.tech/tags/probability.md>), [results](<https://devfeed.tech/tags/results.md>), [sample](<https://devfeed.tech/tags/sample.md>), [search](<https://devfeed.tech/tags/search.md>), [target](<https://devfeed.tech/tags/target.md>), [variable](<https://devfeed.tech/tags/variable.md>)

### AI overview

The proposed framework combines contextual information with known causal graphs to optimize intervention policies for a target variable. Its algorithm jointly selects the policy and the variables on which that policy depends, unifying contextual and causal Bayesian optimization to address cases where either approach alone can yield suboptimal results. The authors derive worst-case and instance-dependent high-probability regret bounds, and report experiments showing sublinear regret and reduced sample complexity in high-dimensional settings.

### Source excerpt

arXiv:2301.12412v5 Announce Type: replace Abstract: We introduce a unified framework for contextual and causal Bayesian optimisation, which aims to design intervention policies maximising the expectation of a target variable. Our approach leverages both observed contextual information and known causal graph structures to guide the search. Within this framework, we propose a novel algorithm that jointly optimises over policies and the sets of variables on which these policies are defined. This thereby extends and unifies two previously distinct approaches: Causal Bayesian Optimisation and Contextual Bayesian Optimisation, while also addressing their limitations in scenarios that yield suboptimal results. We derive worst-case and instance-dependent high-probability regret bounds for our algorithm. We report experimental results across diverse environments, corroborating that our approach achieves sublinear regret and reduces sample complexity in high-dimensional settings.

## SWE-WhatIf: Simulating Real Users of Coding Agents from Recorded Session

DevFeed: [SWE-WhatIf: Simulating Real Users of Coding Agents from Recorded Session](<https://devfeed.tech/articles/swe-whatif-simulating-real-users-of-coding-agents-from-recorded-session-137656.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21095>)

Author: Tae Soo Kim, Tongshuang Wu, Juho Kim

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-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [llms](<https://devfeed.tech/tags/llms.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [recording](<https://devfeed.tech/tags/recording.md>), [session](<https://devfeed.tech/tags/session.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [simulator](<https://devfeed.tech/tags/simulator.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

SWE-WhatIf replays recorded coding-agent sessions by modeling the user's intent, satisfaction criteria, and the conditions that prompt replies. Its simulator adapts to new agent turns while staying grounded in the original recording, addressing why recorded replies cannot simply be replayed when an agent takes a different path. Across 89 real-world sessions, its replies were most similar to real users' and it matched the strongest baseline on rewritten sessions. In tests where agents avoided or repeated actions users had challenged, SWE-WhatIf had a 66.3% win rate for avoiding those actions, significantly above chance. When ranking five LLM coding agents, the top model varied with how users expressed and developed their intent. In a study with 16 users, replaying their sessions changed 14 participants' rankings and informed their future agent use.

### Source excerpt

arXiv:2611.21095v1 Announce Type: cross Abstract: Recorded sessions between users and coding agents offer a way to evaluate how agents complete real-world tasks and interact with users. However, these sessions cannot simply be replayed with new agents, because recorded user replies may no longer apply when an agent takes a different trajectory. We introduce SWE-WhatIf, which replays recorded sessions with new agents by modeling the user's intents, the criteria for satisfying them, and the conditions under which they arise. Using this model, a user simulator generates replies that adapt to unseen agent turns while remaining grounded in the recording. Across 89 real-world sessions, SWE-WhatIf generated the replies most similar to those of real users and matched the strongest baseline when sessions were rewritten. To test adaptation, we replay sessions with agents instructed to avoid or repeat actions that the recorded user pushed back on. SWE-WhatIf produced the highest win rate for avoiding these actions (66.3%), significantly above chance. We further demonstrate its utility by ranking five LLMs as coding agents, where the highest-ranked model depended on how users specified and developed their intents, and a study with 16 users, where replaying their own sessions changed 14 participants' rankings and informed their future agent use.

## Beyond Prediction Residuals: Conformal Regret Calibration for Robust Contextual Linear Optimization

DevFeed: [Beyond Prediction Residuals: Conformal Regret Calibration for Robust Contextual Linear Optimization](<https://devfeed.tech/articles/beyond-prediction-residuals-conformal-regret-calibration-for-robust-contextual-linear-optimization-125487.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11973>)

Author: Lingjie Zhao, Hansheng Jiang, Wei Qi

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

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

Topics: [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decision](<https://devfeed.tech/tags/decision.md>), [framework](<https://devfeed.tech/tags/framework.md>), [linear](<https://devfeed.tech/tags/linear.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [robust](<https://devfeed.tech/tags/robust.md>), [set](<https://devfeed.tech/tags/set.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

Conformal Regret Sets calibrate downstream decision regret for contextual linear optimization instead of calibrating prediction residuals, which may not reflect decision risk. Directly calibrating exact regret makes alternative decisions have unbounded worst-case regret without an externally bounded support, so the method uses SPO+, an upper bound on exact regret, to obtain distribution-free finite-sample marginal guarantees under exchangeability. For linear programs, the calibrated set has polyhedral pieces aligned with the feasible polytope's normal fan; only vertices whose predicted suboptimality gap is at most half the threshold need to be considered. A gap-based certificate also permits an exact early exit when η ≤ 2Γ. In contextual fractional knapsack experiments, continuous refinement lowered the 0.95-quantile and CVaR₀.₉₅ of regret by 9.1% and 13.1% versus nominal predict-then-optimize, while vertex-restricted refinement changed 10.0% of nominal decisions.

### Source excerpt

arXiv:2611.11973v1 Announce Type: cross Abstract: Predict-then-optimize systems convert contextual forecasts into decisions, yet conformal robust optimization typically calibrates prediction residuals rather than downstream loss. For linear optimization, this parameter-space geometry can be badly misaligned with decision risk: large objective perturbations may preserve the optimizer, while small boundary-crossing perturbations may cause substantial regret. We introduce Conformal Regret Sets, a post-hoc, model-agnostic framework that conformalizes an optimization-derived regret surrogate and uses its calibrated level set for minimax-regret refinement. We first show that directly conformalizing exact regret, although sufficient to certify the nominal predict-then-optimize decision, yields a degenerate robust problem: absent an exogenous bounded support, every alternative decision has unbounded worst-case regret. We therefore use SPO+, a pointwise upper bound on exact regret, as the conformal score, obtaining distribution-free finite-sample marginal regret guarantees under exchangeability. For contextual linear programs, the resulting set decomposes into polyhedral pieces aligned with the normal fan of the feasible polytope. A vertex is active if and only if its predicted suboptimality gap is at most half the calibrated threshold $\eta$, enabling local, output-sensitive generation of all relevant pieces. Moreover, if $\Gamma$ is the predicted gap to the closest competing vertex, the nominal and refined decisions admit the sharper worst-case-regret certificate $(\eta-2\Gamma)_+$, with an exact early exit when $\eta\leq 2\Gamma$. Experiments on contextual fractional knapsack validate the geometry and certificates: continuous refinement reduces the $0.95$-quantile and $\operatorname{CVaR}_{0.95}$ of regret by $9.1\%$ and $13.1\%$ relative to nominal PTO, while vertex-restricted refinement changes only $10.0\%$ of nominal decisions.

## A Computational Model of Inclusive Pedagogy: From Understanding to Application

DevFeed: [A Computational Model of Inclusive Pedagogy: From Understanding to Application](<https://devfeed.tech/articles/a-computational-model-of-inclusive-pedagogy-from-understanding-to-application-125101.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.02853>)

Author: Francesco Balzan, Pedro P. Santos, Maurizio Gabbrielli, Mahault Albarracin, Manuel Lopes

Published: 2026-11-10T05:00:00Z

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: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [inclusive design](<https://devfeed.tech/topics/inclusive-design.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-in-education](<https://devfeed.tech/tags/ai-in-education.md>), [classroom](<https://devfeed.tech/tags/classroom.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [education](<https://devfeed.tech/tags/education.md>), [inclusive](<https://devfeed.tech/tags/inclusive.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [strategies](<https://devfeed.tech/tags/strategies.md>), [student](<https://devfeed.tech/tags/student.md>), [support](<https://devfeed.tech/tags/support.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [systems](<https://devfeed.tech/tags/systems.md>), [teaching](<https://devfeed.tech/tags/teaching.md>)

### AI overview

The proposed computational model tests how co-adaptive teacher-student interaction affects learning in a synthetic classroom with students who have unequal access to sensory information. The abstract reports that strategies with bidirectional agency outperform unilateral approaches, where only the teacher or student is active, improving outcomes across all simulated learning types. The model is presented as a framework for testing context-dependent educational ideas and generating hypotheses in adaptable controlled settings. The supplied abstract does not specify the model's implementation or how its results translate to real classrooms.

### Source excerpt

arXiv:2505.02853v1 Announce Type: cross Abstract: Human education transcends mere knowledge transfer, it relies on co-adaptation dynamics -- the mutual adjustment of teaching and learning strategies between agents. Despite its centrality, computational models of co-adaptive teacher-student interactions (T-SI) remain underdeveloped. We argue that this gap impedes Educational Science in testing and scaling contextual insights across diverse settings, and limits the potential of Machine Learning systems, which struggle to emulate and adaptively support human learning processes. To address this, we present a computational T-SI model that integrates contextual insights on human education into a testable framework. We use the model to evaluate diverse T-SI strategies in a realistic synthetic classroom setting, simulating student groups with unequal access to sensory information. Results show that strategies incorporating co-adaptation principles (e.g., bidirectional agency) outperform unilateral approaches (i.e., where only the teacher or the student is active), improving the learning outcomes for all learning types. Beyond the testing and scaling of context-dependent educational insights, our model enables hypothesis generation in controlled yet adaptable environments. This work bridges non-computational theories of human education with scalable, inclusive AI in Education systems, providing a foundation for equitable technologies that dynamically adapt to learner needs.

## Remembering Is Not Enough: Evaluating Timing and Omission in Longitudinal AI Mental Health Support

DevFeed: [Remembering Is Not Enough: Evaluating Timing and Omission in Longitudinal AI Mental Health Support](<https://devfeed.tech/articles/remembering-is-not-enough-evaluating-timing-and-omission-in-longitudinal-ai-mental-health-support-124556.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08721>)

Author: Eli Min, Mohit Chandra, Aamogh Sawant, Mengting Tu, Freya Lin, Ridwan Shams Khan, Reigna El-Yashruti, Christopher L. Smith, Mark Kalinich, John Torous, Munmun De Choudhury

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

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

Topics: [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-chatbots](<https://devfeed.tech/tags/ai-chatbots.md>), [anxiety](<https://devfeed.tech/tags/anxiety.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [ideation](<https://devfeed.tech/tags/ideation.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [llms](<https://devfeed.tech/tags/llms.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mental-health](<https://devfeed.tech/tags/mental-health.md>), [planning](<https://devfeed.tech/tags/planning.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [safety](<https://devfeed.tech/tags/safety.md>), [simulations](<https://devfeed.tech/tags/simulations.md>), [style](<https://devfeed.tech/tags/style.md>), [support](<https://devfeed.tech/tags/support.md>), [timing](<https://devfeed.tech/tags/timing.md>)

### AI overview

Across 14,256 longitudinal simulations grounded in chatbot histories donated by 22 users, advice from a memory-equipped assistant often failed to match users' readiness after suicidal ideation, self-harm, or anxiety crises. The study introduces the Context-Aware and Readiness-Evaluative (CARE) framework, developed with mental health professionals, to assess advice timing and quality, including omissions. Premature recommendations were more common when recovery stalled; revisiting a crisis reduced premature advice but did not reduce lagging advice. Communication style also affected how often and when recommendations appeared. Explicitly unproductive advice was rare, but the assistant often omitted clinician-expected follow-up and next-step planning. The findings suggest that single-response safety checks can miss timing and omission problems across extended support.

### Source excerpt

arXiv:2611.08721v1 Announce Type: cross Abstract: Evaluations of large language models (LLMs) for mental health support commonly focus on the clinical appropriateness of individual responses, potentially overlooking failures that emerge across extended interactions. As AI assistants accumulate memory of users' circumstances and prior disclosures, this raises an accountability question: Do AI chatbots provide appropriate support as users' needs evolve? We investigate by analyzing 14,256 longitudinal simulations grounded in donated chatbot histories from 22 users, examining how a memory-equipped assistant responds to suicidal ideation, self-harm, and anxiety crises across recovery trajectories and communication styles. We introduce the Context-Aware and Readiness-Evaluative (CARE) framework, developed with mental health professionals, to assess the timing and quality of advice, including omissions. Advice was less aligned with users' readiness after a crisis than in matched control stretches of the same conversation, largely because of premature recommendations, which were most common when recovery stalled. Revisiting a crisis reduced premature advice but not lagging advice, and users' communication style changed how often and when the assistant gave recommendations. Although explicitly unproductive advice was rare, the assistant frequently omitted clinician-expected support such as follow-up and planning for next steps. These findings show the limits of single response-level safety evaluation and the need to assess timing, omission, and consistency across users when holding AI systems accountable for longitudinal support.

## SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats

DevFeed: [SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats](<https://devfeed.tech/articles/suichat-cn-benchmarking-contextual-suicide-risk-assessment-in-chinese-group-chats-124429.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.27911>)

Author: Xiangyu Wang, Zhiwei Yu, Chengze Du, Dingchang Wang, Yuhan Ye, Fangyu Zheng

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

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

Topics: [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Audit-then-score](<https://devfeed.tech/topics/audit-then-score.md>)

Tags: [assessment](<https://devfeed.tech/tags/assessment.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [detection](<https://devfeed.tech/tags/detection.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [group-chats](<https://devfeed.tech/tags/group-chats.md>), [risk](<https://devfeed.tech/tags/risk.md>), [risk-assessment](<https://devfeed.tech/tags/risk-assessment.md>), [suicide](<https://devfeed.tech/tags/suicide.md>)

### AI overview

SuiChat-CN benchmarks contextual suicide risk assessment in Chinese Telegram group chats, where fragmented, multi-party messages can make isolated posts insufficient. It comprises 13,312 conversational segments from 1,406 users, covering 258,228 messages. The authors form segments using signal-word extraction and bidirectional context expansion, then annotate user risk levels through an expert-validated, LLM-assisted process. Experiments with pretrained language models and more than 40 LLMs find context essential to reliable assessment; fine-tuning and partial-context evaluation also expose challenges for early detection. Because of ethical and sensitivity concerns, the dataset is not public and is available upon reasonable request to accredited mental health and suicide-prevention research institutions.

### Source excerpt

arXiv:2605.27911v2 Announce Type: replace Abstract: Suicide is a critical global public health challenge, causing approximately 720,000 deaths each year and calling for timely, effective prevention strategies. Existing computational studies primarily focus on post-based social media platforms such as Twitter and Weibo, leaving instant messaging environments such as Telegram underexplored. Yet group chats pose distinct challenges: messages are short, fragmented, multi-party, and often rely on implicit or culturally specific expressions, making isolated post-level analysis insufficient. We introduce SuiChat-CN, a Chinese group-chat benchmark for contextual suicide risk assessment. We collect public Telegram group-chat data, construct coherent conversational segments through signal-word extraction and bidirectional context expansion, and annotate user risk levels with an expert-validated, LLM-assisted paradigm. SuiChat-CN contains 13,312 contextual segments from 1,406 users, covering 258,228 raw chat messages. Extensive experiments with PLMs and more than 40 LLMs demonstrate that contextual information is essential for reliable risk assessment, while fine-tuning and partial-context evaluation further reveal the challenges of early detection in multi-party conversations. Due to ethical and sensitivity concerns, the dataset is not publicly released but will be shared with accredited mental health and suicide-prevention research institutions upon reasonable request.

## A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing

DevFeed: [A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing](<https://devfeed.tech/articles/a-generative-model-of-contextual-integrity-appropriate-vs-inappropriate-information-sharing-120304.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08284>)

Author: Omer Ebead, Claude Formanek, Joel Z. Leibo

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

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

Topics: [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [context](<https://devfeed.tech/topics/context.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [disclosure](<https://devfeed.tech/tags/disclosure.md>), [generative](<https://devfeed.tech/tags/generative.md>), [information](<https://devfeed.tech/tags/information.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [language](<https://devfeed.tech/tags/language.md>), [model](<https://devfeed.tech/tags/model.md>), [sharing](<https://devfeed.tech/tags/sharing.md>)

### AI overview

The study models contextual integrity through simulated conversations between two large language model actors: one holds private information and the other seeks it. It examines how sharing and refusal vary with the situation, the holder's decision logic and disposition, and the underlying language model. Actors shared information with rightful recipients when needed, but also disclosed it to people not entitled to receive it. The model offers a way to study how disclosure and refusal develop as conversational situations and actors vary.

### Source excerpt

arXiv:2611.08284v1 Announce Type: new Abstract: Contextual integrity (CI) holds that appropriate information flow depends on context-specific norms. The same disclosure may be appropriate in one context and inappropriate in another. We build a generative model of contextual integrity to study information sharing through simulated conversations. Two actors played by large language models exchange messages, with one holding private information and the other seeking it. We examine how sharing and refusal vary with the situation, the holder's decision logic, disposition, and the underlying language model. Actors shared information with the rightful recipients when it was needed, but also disclosed it to people who were not entitled to receive it. The model provides a way to study how disclosure and refusal develop through conversation as the situations and the actors vary.

## PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

DevFeed: [PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation](<https://devfeed.tech/articles/prime-predictive-routing-of-interventions-by-modeling-effects-for-scientific-ideation-115414.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03055>)

Author: Fengxian Ji, Xie Yu, Zhexuan Cui, Yuke Li, Zirui Song, Fan Zhang, Qian Jiang, Jingpu Yang, Xiuying Chen, Preslav Nakov, Zhuohan Xie

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

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

Topics: [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [actions](<https://devfeed.tech/tags/actions.md>), [align](<https://devfeed.tech/tags/align.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [better](<https://devfeed.tech/tags/better.md>), [but](<https://devfeed.tech/tags/but.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [effect](<https://devfeed.tech/tags/effect.md>), [effects](<https://devfeed.tech/tags/effects.md>), [either](<https://devfeed.tech/tags/either.md>), [execution](<https://devfeed.tech/tags/execution.md>), [existing](<https://devfeed.tech/tags/existing.md>), [ideation](<https://devfeed.tech/tags/ideation.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [routing](<https://devfeed.tech/tags/routing.md>)

### AI overview

PRIME routes feedback to revision scopes by modeling how alternative interventions may affect a successor idea, addressing a mismatch between where a weakness appears and which part should be revised. Its three stages interpret feedback across the problem, hypothesis, and solution; compare scope-conditioned interventions using lightweight rollouts; and turn the selected intervention into an ordered plan with actions, preservation constraints, and dependencies. In tests across four benchmarks, two ideators, and fixed- and open-problem settings, PRIME improved successor quality and routing reliability over strong baselines. Ablating counterfactual routing lowered quality from 3.463 to 1.960 and raised route regret from 0.426 to 1.929.

### Source excerpt

arXiv:2611.03055v1 Announce Type: new Abstract: Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor. We term this phenomenon diagnosis-intervention mismatch. We introduce Predictive Routing of Interventions by Modeling Effects (PRIME), a plug-and-play feedback-to-revision decision layer for existing scientific ideators. PRIME operates in three stages: (1) Structural Attribution interprets feedback over the problem-hypothesis-solution structure without fixing a revision target; (2) Counterfactual Routing constructs alternative scope-conditioned interventions and compares their projected successor utility and risks through lightweight rollouts; and (3) Intervention Execution compiles the selected intervention into an ordered generator-facing plan with semantic actions, preservation constraints, and dependency requirements for successor generation. We validate diagnosis intervention mismatch on 112 human-annotated idea-feedback pairs. Across four benchmarks, two ideators, and fixed- and open-problem settings, PRIME improves successor quality and routing reliability over strong baselines; removing counterfactual routing reduces quality from 3.463 to 1.960 and increases route regret from 0.426 to 1.929, confirming cross-scope effect modeling as the primary source of its gains.

## Zero Trust-Enabled Adaptive Incident Response using Hierarchical Reinforcement Learning

DevFeed: [Zero Trust-Enabled Adaptive Incident Response using Hierarchical Reinforcement Learning](<https://devfeed.tech/articles/zero-trust-enabled-adaptive-incident-response-using-hierarchical-reinforcement-learning-109032.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.38146>)

Author: Jisoo Lee, Bhagath Singh Bondili, Harshith Doppalapudi, Gwynith Godin, Nathaniel D. Bastian, Ankit Shah

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [AI in cybersecurity](<https://devfeed.tech/topics/ai-in-cybersecurity.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>), [trust](<https://devfeed.tech/tags/trust.md>), [zero-trust](<https://devfeed.tech/tags/zero-trust.md>)

### AI overview

ZT-AIR applies zero trust architecture and hierarchical reinforcement learning to adapt incident response to identity-centric threats. It learns context-aware trust decisions, separates strategic prioritization from tactical execution, and treats zero-trust controls as actions while optimizing security and operational continuity together. Experiments across adversarial strategies, network scales, and defense environments report a balance achieved through frequent, minimally disruptive interventions; practitioner validation supports practical viability. The supplied text does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2610.38146v1 Announce Type: new Abstract: Modern enterprises increasingly operate through complex information systems (IS) enabled by cloud computing, remote and hybrid work practices, and digitally integrated supply chains. These structural shifts have expanded organizational attack surfaces and weakened traditional perimeter-based trust assumptions, giving rise to new and persistent forms of cyber threats. In response, adversaries have shifted toward identity-centric, trust-based intrusion techniques that exploit legitimate access within organizational systems. This evolution has created a pronounced speed asymmetry, whereby attackers can adapt and act at machine speed while defenders remain constrained by reactive or rule-based incident response (IR) processes. Drawing on design science research, we propose ZT-AIR, an adaptive IR artifact that uses zero trust architecture as its design theory and hierarchical reinforcement learning as its kernel theory. ZT-AIR learns context-aware trust decisions, separates strategic prioritization from tactical execution, encodes zero-trust controls as actions, and jointly optimizes security effectiveness and operational continuity. Experimental results across diverse adversarial strategies, network scales, and defense environments show that ZT-AIR achieves a strong balance between security and continuity through frequent, minimally disruptive interventions. Practitioner validation further confirms the design's practical viability. This study contributes to IS research by extending computational design science from threat identification to response execution, theorizing zero trust architecture for adaptive IR, and deriving reusable design principles for adaptive decision support artifacts.

## Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use

DevFeed: [Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use](<https://devfeed.tech/articles/evidence-grounded-slm-behavioral-prediction-architecture-for-future-assistance-use-99963.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32193>)

Author: Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen, Jouni Isoaho

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

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

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Uncertainty quantification LLMs](<https://devfeed.tech/topics/uncertainty-quantification-llms.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [digital sovereignty](<https://devfeed.tech/topics/digital-sovereignty.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [behavioral-prediction](<https://devfeed.tech/tags/behavioral-prediction.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data-sovereignty](<https://devfeed.tech/tags/data-sovereignty.md>), [device](<https://devfeed.tech/tags/device.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [local](<https://devfeed.tech/tags/local.md>), [low-level](<https://devfeed.tech/tags/low-level.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [slm](<https://devfeed.tech/tags/slm.md>), [slms](<https://devfeed.tech/tags/slms.md>), [small-language-models](<https://devfeed.tech/tags/small-language-models.md>), [structured](<https://devfeed.tech/tags/structured.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Evidence-Grounded Local Behavioral Prediction (ELBP) combines deterministic interaction processing, dual-view behavioral representations, small language model prediction, and evidence verification with abstention to forecast future assistance use from interaction events. Across three instruction-tuned models of 3B parameters or fewer, Qwen2.5-3B with ELBP achieved full-set F1 0.80 and PR-AUC 0.84, improving relative to raw-event prompting and XGBoost; its full-set ECE was also lower than with raw-event prompting. Adding verification and abstention raised selective F1 to 0.84 at 91% coverage, with 96% evidence support. These abstract-level results suggest structured inputs and evidence checks can improve selective prediction; they do not establish performance beyond the reported evaluation.

### Source excerpt

arXiv:2610.32193v1 Announce Type: new Abstract: Users often exhibit changes in interaction behavior before explicitly seeking assistance, enabling systems to anticipate future assistance use. This is especially important in high-stakes environments, where delayed assistance can have operational, financial, or safety consequences. However, conventional Large Language Models (LLMs) are often unsuitable for continuous on-device behavioral prediction because of their computational and memory demands. Behavioral patterns are also highly individual and device-specific, motivating local processing that preserves privacy and data sovereignty. Small Language Models (SLMs) offer a promising alternative, but their ability to reason reliably over low-level sequential interaction events remains underexplored. This study introduces Evidence-Grounded Local Behavioral Prediction (ELBP), a four-layer architecture combining deterministic interaction processing, dual-view behavioral representation, SLM-based prediction, and evidence verification with abstention. Three instruction-tuned models of 3B parameters or fewer were evaluated using raw, structured, dual-view, and complete ELBP configurations. The best-performing model, Qwen2.5-3B with ELBP, achieved a full-set F1-score of 0.80 and PR-AUC of 0.84, representing a 15.9\% relative improvement over raw-event prompting and 17.6\% over XGBoost, while full-set ECE decreased by 43.2\% relative to raw-event prompting. With evidence verification and abstention, selective F1 increased to 0.84 at 91\% coverage and evidence support reached 96\%. These results show that structured behavioral representation and evidence-verified selective prediction can improve the reliability of behavioral forecasting in SLMs.

## Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization

DevFeed: [Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization](<https://devfeed.tech/articles/bridging-exploration-and-persona-information-directed-dueling-for-test-time-agent-personalization-99854.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.24385>)

Author: Jie Mao, Pingchen Lu, Xiangyi Wang, Hengquan Huang, Shuang Qiu, Min Zhang, Zhongxiang Dai

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

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

Topics: [personalization](<https://devfeed.tech/topics/personalization.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [thompson sampling](<https://devfeed.tech/topics/thompson-sampling.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [bandit](<https://devfeed.tech/tags/bandit.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bt](<https://devfeed.tech/tags/bt.md>), [budget](<https://devfeed.tech/tags/budget.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [generation](<https://devfeed.tech/tags/generation.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [neural](<https://devfeed.tech/tags/neural.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [reference](<https://devfeed.tech/tags/reference.md>), [signal](<https://devfeed.tech/tags/signal.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [user](<https://devfeed.tech/tags/user.md>), [utility](<https://devfeed.tech/tags/utility.md>)

### AI overview

ID-TAP adapts an LLM agent's persona from binary comparisons between candidate responses. It combines a query-conditioned neural utility model, which shares evidence across queries while retaining query-specific scores, with a lightweight Bradley-Terry explorer that efficiently evaluates hypothetical challengers. Similarity-weighted warm starts transfer comparison evidence across related queries. Across seven user-conditioned generation benchmarks with reference- and model-based preference simulators, ID-TAP achieved the strongest aggregate performance among the evaluated baselines under a fixed budget of ten comparison rounds.

### Source excerpt

arXiv:2610.24385v2 Announce Type: replace Abstract: Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparisons between candidate responses as the online signal. We present ID-TAP, a scalable, IDS-inspired neural dueling-bandit framework for large discrete persona spaces. ID-TAP combines a query-conditioned neural utility model with a lightweight Bradley-Terry explorer, and transfers comparison evidence across related queries through similarity-weighted warm starts. The neural model shares statistical strength across queries while preserving query-specific scores, and efficient BT updates score hypothetical challengers. Across seven user-conditioned generation benchmarks under reference- and model-based preference simulators, ID-TAP achieves the strongest aggregate performance among the evaluated baselines within a fixed ten-round comparison budget. These results support information-directed challenger selection as an effective design for test-time persona adaptation.

## Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use

DevFeed: [Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use](<https://devfeed.tech/articles/memory-aware-reward-modeling-learning-human-preferences-for-llm-memory-use-98189.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.31272>)

Author: Yijiang River Dong, Zexue He, Cheng Yu, Tiancheng Hu, Michael J Ryan, Jan Batzner, Zheng Hui, Shaolong Wu, Orestis Papakyriakopoulos, Alex Pentland, Nigel Collier, Jiaxin Pei

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

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

Topics: [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [learning](<https://devfeed.tech/tags/learning.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-memory](<https://devfeed.tech/tags/llm-memory.md>), [memory](<https://devfeed.tech/tags/memory.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [reward](<https://devfeed.tech/tags/reward.md>)

### AI overview

The study finds that using personal memory does not reliably make assistant responses more preferable to users. It collected about 1,000 pairwise judgments from 87 participants based on their own ChatGPT queries and memories; users sometimes strongly preferred responses generated without memory. Automatic evaluators agreed only limitedly with users and favored memory-conditioned responses more often. A reward model trained on user judgments reached 72.8% preference prediction accuracy, outperforming the reported baselines. The findings support evaluating and optimizing memory use against the preferences of the people whose information is used.

### Source excerpt

arXiv:2610.31272v1 Announce Type: cross Abstract: Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To study this gap, we collect approximately 1,000 pairwise judgments from 87 participants using their own ChatGPT queries and personal memories. We find that memory-conditioned responses are not consistently preferred over responses generated without memory and in some cases, users strongly prefer the latter. Automatic evaluators also show limited agreement with users and favor memory-conditioned responses substantially more often than users do. Motivated by these gaps, we introduce a memory-aware reward model that learns from user judgments, achieving 72.8\% preference prediction accuracy and outperforming the existing baselines. Our findings motivate evaluation and optimization objectives that align memory use with the preferences of the people whose information is being used.

## Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle

DevFeed: [Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle](<https://devfeed.tech/articles/open-and-emergent-problems-in-agentic-privacy-and-security-a-contextual-angle-65198.md>)

Original publisher: [Read original article](<https://research.google/blog/open-and-emergent-problems-in-agentic-privacy-and-security-a-contextual-angle/>)

Published: 2026-10-05T21:08:31Z

Content type: article

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Security, Privacy and Abuse Prevention](<https://devfeed.tech/topics/security-privacy-and-abuse-prevention.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Dynamic authorization rules](<https://devfeed.tech/topics/dynamic-authorization-rules.md>), [GitHub Agentic Workflows](<https://devfeed.tech/topics/github-agentic-workflows.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [education-innovation](<https://devfeed.tech/tags/education-innovation.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [general-science](<https://devfeed.tech/tags/general-science.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [open](<https://devfeed.tech/tags/open.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [security](<https://devfeed.tech/tags/security.md>), [security-privacy-and-abuse-prevention](<https://devfeed.tech/tags/security-privacy-and-abuse-prevention.md>)

### AI overview

A Google Research workshop report outlines research challenges for trustworthy autonomous AI agents, focusing on contextual privacy and security. It proposes contextual policy engines to evaluate actions and information flows, alongside advances in models, user interaction, and evaluations for multi-agent systems.

### Source excerpt

Education Innovation

## How Klarna's AI assistant redefined customer support at scale for 85 million active users

DevFeed: [How Klarna's AI assistant redefined customer support at scale for 85 million active users](<https://devfeed.tech/articles/how-klarna-s-ai-assistant-redefined-customer-support-at-scale-for-85-million-active-users-78292.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/customers-klarna>)

Author: LangChain Accounts

Published: 2026-08-25T19:38:39Z

Content type: article

Language: en

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

Topics: [Langgraph](<https://devfeed.tech/topics/langgraph.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Usability](<https://devfeed.tech/topics/usability.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>)

Tags: [agent-architecture](<https://devfeed.tech/tags/agent-architecture.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [customer-support](<https://devfeed.tech/tags/customer-support.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [klarna](<https://devfeed.tech/tags/klarna.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>)

### AI overview

Klarna built a customer support AI assistant using LangGraph and LangSmith to route requests, handle escalations, and refine agent performance through testing and evaluations. The article reports an 80% reduction in average query resolution time and automation of about 70% of repetitive support tasks over nine months.

### Source excerpt

Klarna's AI assistant is revolutionizing the personal shopping experience, including customer service and productivity. See how they used LangGraph and LangSmith to achieve 80% faster customer resolution times.

## OpenAI and Dell partner to bring Codex to hybrid and on-premise enterprise environments

DevFeed: [OpenAI and Dell partner to bring Codex to hybrid and on-premise enterprise environments](<https://devfeed.tech/articles/openai-and-dell-partner-to-bring-codex-to-hybrid-and-on-premise-enterprise-environments-6373.md>)

Original publisher: [Read original article](<https://openai.com/index/dell-codex-enterprise-partnership>)

Published: 2026-05-18T10:00:00Z

Content type: news

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [codex](<https://devfeed.tech/topics/codex.md>), [dell](<https://devfeed.tech/topics/dell.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [enterprise data protection](<https://devfeed.tech/topics/enterprise-data-protection.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-factory](<https://devfeed.tech/tags/ai-factory.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [company](<https://devfeed.tech/tags/company.md>), [data](<https://devfeed.tech/tags/data.md>), [dell](<https://devfeed.tech/tags/dell.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [on-premise](<https://devfeed.tech/tags/on-premise.md>), [openai](<https://devfeed.tech/tags/openai.md>), [partner](<https://devfeed.tech/tags/partner.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

OpenAI and Dell are collaborating to make Codex usable closer to enterprise data and workflows in hybrid and on-premises environments. Codex will connect with Dell AI Data Platform, which businesses use to store, organize, and govern on-premises data. The companies will also explore connections between Codex, ChatGPT Enterprise, and API-based solutions and Dell AI Factory to prepare data, manage systems of record, run tests, and deploy AI applications integrated with Dell infrastructure. The stated aim is to give enterprises a practical path to production with controls and access to internal context, supporting software development and broader knowledge work. The AI Factory connection is described as exploratory.

### Source excerpt

OpenAI and Dell partner to bring Codex to hybrid and on-premise environments, helping enterprises deploy AI coding agents securely across data and workflows.

## Teradata AI Services Deliver Production-Ready Agentic Use Cases that Drive Measurable Business Impact

DevFeed: [Teradata AI Services Deliver Production-Ready Agentic Use Cases that Drive Measurable Business Impact](<https://devfeed.tech/articles/teradata-ai-services-deliver-production-ready-agentic-use-cases-that-drive-measurable-business-impact-81137.md>)

Original publisher: [Read original article](<https://www.teradata.com/press-releases/2025/teradata-ai-services-deliver-production-ready-agentic-use-cases>)

Author: Jennifer Donahue

Published: 2025-10-28T07:00:00Z

Content type: news

Language: en

Sources: [Teradata News](<https://devfeed.tech/sources/teradata-news.md>)

Topics: [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Open Data](<https://devfeed.tech/topics/open-data.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-services](<https://devfeed.tech/tags/ai-services.md>), [article](<https://devfeed.tech/tags/article.md>), [automation](<https://devfeed.tech/tags/automation.md>), [business](<https://devfeed.tech/tags/business.md>), [business-context](<https://devfeed.tech/tags/business-context.md>)

### AI overview

Teradata announced AI Services, a sprint-based consulting and deployment offering intended to help enterprises move AI pilots into production. It combines expert guidance on use case prioritization and governance with Teradata tools, reusable data products, deployment support, and ongoing model operations. The services are generally available across cloud and on-premises environments.

### Source excerpt

Sprint-based services, with flexible offerings and use case-driven methodology, meets organizations at any AI maturity level to accelerate deployment from concept to scale

## AI evals for MCP in AIOps

DevFeed: [AI evals for MCP in AIOps](<https://devfeed.tech/articles/ai-evals-for-mcp-in-aiops-57176.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/AI-evals-for-MCP-in-AIOps>)

Author: Zichuan Xiong, Larissa Dornelles, Scott Juang

Published: 2025-07-31T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Risk](<https://devfeed.tech/topics/risk.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Security](<https://devfeed.tech/topics/security.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Availability](<https://devfeed.tech/topics/availability.md>)

Tags: [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [ai-evals](<https://devfeed.tech/tags/ai-evals.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [availability](<https://devfeed.tech/tags/availability.md>), [blog](<https://devfeed.tech/tags/blog.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [context-aware-ai](<https://devfeed.tech/tags/context-aware-ai.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

This article examines how AI evaluations can be embedded into MCP-driven AIOps workflows. It describes how context-aware agents retrieve live operational data and explains risks including hallucinations, compliance gaps, security vulnerabilities, latency, inconsistent results and cascading failures.

### Source excerpt

AI evals for MCP in AIOps