arXiv：cs.AI· Xingjian Diao, Tianyu Yang, Wenjun Huang, Xiangchi Yuan, Chunhui Zhang, Xingchen Zhao, Weiyi Wu, Haotian Xu, Soroush Vosoughi, Xiangliang Zhang, Jiang Gui·· 22 小时前
ECHO：面向工具使用智能体的责任感知信用分配框架
Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
AI 导读
研究者提出 Error-Chain-Aware Optimization（ECHO），一个责任感知的信用分配框架，将责任识别与信用分配分离，用冻结的 judge 区分新引入错误、继承后果、漏纠与成功纠正，并对共享下游后果只计一次、通过 source-funded recovery 约束自致错误的修复奖励。
正文
Authors:Xingjian Diao, Tianyu Yang, Wenjun Huang, Xiangchi Yuan, Chunhui Zhang, Xingchen Zhao, Weiyi Wu, Haotian Xu, Soroush Vosoughi, Xiangliang Zhang, Jiang Gui
Abstract:Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited from an earlier decision, while multiple responsible decisions may share the same downstream consequence or participate in later recovery. We introduce Error-Chain-Aware Optimization (ECHO), a responsibility-aware credit assignment framework that separates responsibility identification from credit allocation. A frozen judge combines retrospective trajectory analysis with decision-time assessment from the policy-visible prefix to distinguish newly introduced errors, inherited consequences, missed corrections, and successful corrections. ECHO then counts shared downstream consequences once across responsible decisions and constrains rewards for repairing self-induced errors through source-funded recovery, producing bounded action-level supervision alongside terminal supervision. Experiments on six diverse tool-use benchmarks at both 4B and 8B scales show strong and consistent improvements over the compared baselines, with ECHO achieving the highest score on five of six benchmarks at each scale. These results support decision responsibility as a useful basis for fine-grained credit assignment in tool-use agents. Our code is available at this https URL.
| Comments: | 29 pages |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16027 [cs.CL] |
| (or arXiv:2610.16027v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16027 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xingjian Diao [view email]
[v1]
Mon, 12 Oct 2026 00:52:30 UTC (445 KB)
来源：arXiv：cs.AI · arxiv.org