arXiv：cs.AI· Lin Wu, Shu Yao, Yuheng Wang, Jingru Fan, Huatao Li, Yihan Li, Liu Yixuan, Cheng Liu, Jian Chang, Zeyu Zhao, Aohua Zhang, Huiying Zhao, Shuyuan Zhu, Chen Qian·· 17 小时前
CoEvoke：为轨迹采集激发多智能体协作
CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection
AI 导读
CoEvoke 是一个跨域框架，通过可控扰动制造可恢复的困难、并用受限参考引导调查，在轨迹采集阶段激发多智能体之间的检查、反馈与修复交互。其数据集包含 4,567 条可重建轨迹，覆盖 4,130 个软件工程与推理任务；在 2,287 个同任务对上，七个扰动组的反馈提升达 47.72-100 个百分点。
正文
Authors:Lin Wu, Shu Yao, Yuheng Wang, Jingru Fan, Huatao Li, Yihan Li, Liu Yixuan, Cheng Liu, Jian Chang, Zeyu Zhao, Aohua Zhang, Huiying Zhao, Shuyuan Zhu, Chen Qian
Abstract:Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or repeat unsuccessful attempts without useful correction. We introduce CoEvoke, a cross-domain framework that evokes these interactions during trajectory collection. Controlled perturbations create recoverable difficulties, while restricted reference-based guidance directs investigation. The resulting dataset contains 4,567 reconstructable trajectories over 4,130 software-engineering and reasoning tasks, linking public interactions to evidence, decisions, and task-native outcomes. Separate experiments over 2,287 same-task pairs show feedback increases of 47.72-100 percentage points across seven perturbation groups; guidance has smaller, model-dependent effects. With identical training tasks, decision-record counts, and updates, perturbation-enriched judge training improves ACPBench-Hard success from 35.38% to 42.12% (+6.73 points). SWE verifier training gains 7.60-9.40 points over interface-matched untrained references. Workflow and post-training evaluations preserve task-solving topology with unperturbed inputs and no private-reference guidance. These results support designing collection conditions to obtain corrective supervision that improves collaborative decisions with frozen solving agents.
| Comments: | 14 pages, 4 figures, 3 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.14021 [cs.LG] |
| (or arXiv:2610.14021v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14021 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lin Wu [view email]
[v1]
Tue, 29 Sep 2026 13:54:06 UTC (1,478 KB)
来源：arXiv：cs.AI · arxiv.org