# Seq@K: Evaluating Language Models Under Sequential Feedback

DevFeed: [Seq@K: Evaluating Language Models Under Sequential Feedback](<https://devfeed.tech/articles/seq-k-evaluating-language-models-under-sequential-feedback-107976.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37859>)

Author: Thomson Yen, Gilbert Yang, Naimeng Ye, Minghui Chen, Dong Xia, Tianyi Shen, Yechan Jeon, Yaqin Chen, Daksh Mittal, Fangyu Wu, Hongseok Namkoong

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

Content type: article

Language: en

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

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [metric](<https://devfeed.tech/tags/metric.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [model-selection](<https://devfeed.tech/tags/model-selection.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [rankings](<https://devfeed.tech/tags/rankings.md>), [systems](<https://devfeed.tech/tags/systems.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

Seq@K evaluates whether a language model can solve a problem within K sequential attempts, receiving feedback after each failure. Unlike Pass@1 or Pass@K, it measures how models use feedback; unlike long-horizon agent benchmarks, it isolates refinement. Across 7 benchmarks and 16 frontier models, Seq@K often changes model rankings and Pareto frontiers, while the gains from selecting an optimal configuration can widen or shrink compared with Pass@K. Examining attempt trajectories can show how quickly models address feedback and how strongly they stick to prior answers. The abstract also reports that feedback design affects refinement, so feedback loops should be designed and benchmarked for the systems using them.

## Source excerpt

arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K, a natural evaluation protocol that measures whether a model can solve a problem within K sequential attempts, provided feedback after each previous failure. Unlike multi-turn agentic benchmarks that examine long-horizon planning, Seq@K isolates and formalizes the core capability of refinement from feedback. We evaluate Seq@K on a suite of 7 benchmarks and 16 frontier models, and show that Seq@K reveals a materially different model-selection landscape: under Seq@K, (1) model rankings often differ, (2) the Pareto frontiers admit more efficient configurations and (3) the gains from choosing the optimal model configuration can widen or shrink relative to those of Pass@K. We further show that analyzing model trajectories under Seq@K helps characterize iterative refinement behavior, such as the rate at which models address issues raised in feedback, or how rigidly they hold onto their own answers. Finally, we study how the nature of feedback affects models' iterative refinement, showing that practitioners must carefully design and benchmark the feedback loops of iterative agentic systems. Together, these results establish how Seq@K offers a more faithful metric for intelligent systems that typically operate in such feedback loop, and the necessity to consider Seq@K in evaluating models for these systems.