arXiv cs.CL· Wenbo Gao, Renxi Liu, Xian Wang, Fang Guo, Shuai Yang, Xi Chen, Hui-Ling Zhen, Hanting Chen, Weizhe Lin, Xiaosong Li, Yaoyuan Wang·· 11 小时前AI 评分35
AgentCollab：面向高效 LLM 智能体的自评估驱动协作范式
AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
AI 导读
AgentCollab 是一个自驱动的协作推理框架，在智能体执行过程中动态协调不同推理能力的模型，用智能体自身的反思信号判断当前推理轨迹是否有效推进，仅在必要时将控制权升级到更强的推理层级。该框架还引入难度感知的累积升级策略，依据近期失败信号分配额外推理预算，实验采用小模型加大模型的两级设置，在多步智能体基准上持续改善 LLM 智能体的准确率-效率帕累托前沿。代码已公开。
正文 · 原文
Authors:Wenbo Gao, Renxi Liu, Xian Wang, Fang Guo, Shuai Yang, Xi Chen, Hui-Ling Zhen, Hanting Chen, Weizhe Lin, Xiaosong Li, Yaoyuan Wang
Abstract:Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at different capability-cost levels offer complementary advantages: lower-cost models enable fast execution but may struggle on difficult reasoning segments, while stronger models provide more robust reasoning at higher computational cost. We present AgentCollab, a self-driven collaborative inference framework that dynamically coordinates models with different reasoning capacities during agent execution. Instead of relying on external routing modules, the framework uses the agent's own self-reflection signal to determine whether the current reasoning trajectory is making meaningful progress, and escalates control to a stronger reasoning tier only when necessary. To further stabilize long-horizon execution, we introduce a difficulty-aware cumulative escalation strategy that allocates additional reasoning budget based on recent failure signals. In our experiments, we instantiate this framework using a two-level small-large model setting. Experiments on diverse multi-step agent benchmarks show that AgentCollab consistently improves the accuracy-efficiency Pareto frontier of LLM agents. The code is available at this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2603.26034 [cs.CL] |
| (or arXiv:2603.26034v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2603.26034 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.18653/2026.emnlp-main.2400
DOI(s) linking to related resources |
Submission history
From: Wenbo Gao [view email]
[v1]
Fri, 27 Mar 2026 03:07:34 UTC (265 KB)
[v2]
Fri, 30 Oct 2026 09:58:36 UTC (268 KB)
来源：arXiv cs.CL · arxiv.org