智能体
arxiv.org ·
DynSTEER：面向智能体的动态分阶段轨迹评估与执行时审查
该论文针对 LLM 智能体长程任务中轨迹评估的粒度难题：整条轨迹验证过粗、单步打分过细且噪声大、成本高，单一参考轨迹范式难以覆盖合法执行路径的多样性。作者提出 DynSTEER，在关键执行节点切分 rollout 进行分阶段动态评估，并按阶段结果自适应选择多层级审查策略；同时从公开任务视图编译路径容忍的里程碑图，在不泄漏参考的前提下保留多种合法路径，并支持提前终止不可恢复的执行。摘要报告评估区分度较原生评估提升 85.2%，所有模型对差异具统计显著性，失败 rollout 执行步数节省 45.41%。
AI推荐理由 arXiv 新论文（v2，2026-09-15 修订），作者与摘要信息完整，属可验证的研究首发。核心新信息是提出 DynSTEER 分阶段轨迹评估框架：按关键执行节点切分 rollout、依据阶段结果自适应调整多层级审查策略，并从公开任务视图编译路径容忍的里程碑图以避免参考泄漏，同时支持终止不可恢复的执行。摘要给出三项量化结果：评估区分度较原生评估提升 85.2%、所有模型对均具统计显著性差异、失败 rollout 节省 45.41% 执行步数。局限在于仅有摘要级证据，未提供数据集、基线细节与复现材料，指标口径无法独立核验，且尚未见同行评审或第三方复现。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.14637 (cs)
[Submitted on 13 Sep 2026 (v1), last revised 15 Sep 2026 (this version, v2)]
Title:DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents
Authors:Zhichao Shi, Xuhui Jiang, Wenjie Zhang, Xiaojun Wu, Cehao Yang, Chengjin Xu, Jian Guo, Yuanzhuo Wang
View a PDF of the paper titled DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents, by Zhichao Shi and 7 other authors
View PDF
HTML (experimental)
Abstract:Large language model agents are increasingly deployed for long-horizon task execution, raising a central granularity question for trajectory evaluation: whole-trajectory verification is too coarse to capture concrete failures and their associated evidence in long trajectories, while atomic-step scoring is too fine-grained, noise-sensitive, and computationally expensive. This granularity gap makes a single-reference trajectory paradigm inadequate for assessing the rich space of valid agent execution paths and delays timely feedback and early stopping in long-horizon tasks. To address these issues, we propose DynSTEER, a dynamic stage-wise framework for agent trajectory evaluation. DynSTEER bridges the granularity gap through stage-wise dynamic evaluation that segments rollouts at key execution nodes and adapts its multi-tier review strategy based on stage-level results; it compiles a path-tolerant milestone graph from public task views to preserve diverse legal paths without reference leakage; and it supports terminating unrecoverable agent executions to curb resource waste. Experiments show that DynSTEER improves evaluation discriminability by 85.2\% over native evaluation, separates all model pairs with statistical significance, and saves 45.41\% of execution steps on failed rollouts.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.14637 [cs.AI]
(or
arXiv:2609.14637v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.14637
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Zhichao Shi [view email]
[v1]
Sun, 13 Sep 2026 16:18:03 UTC (652 KB)
[v2]
Tue, 15 Sep 2026 10:27:42 UTC (376 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents, by Zhichao Shi and 7 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)