arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26034cs.CL
收藏

AgentCollab: 一种以自我评估驱动的高效大语言模型代理协作范式

AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents

Huawei(华为);Hong Kong Polytechnic University(香港理工大学)

Wenbo Gao, Renxi Liu, Xian Wang, Fang Guo, Shuai Yang, Xi Chen, Hui-Ling Zhen, Hanting Chen, Weizhe Lin, Xiaosong Li, Yaoyuan Wang

AI总结:

本文提出AgentCollab框架,通过自我反思信号动态协调不同推理能力的模型,提升LLM代理在复杂任务中的准确性和效率。

摘要:

自主代理通过长周期推理和工具交互执行复杂任务,其中执行效率与推理鲁棒性之间存在根本性权衡。不同能力-成本水平的模型提供互补优势:低成本模型能快速执行但可能在困难推理段落中表现不佳,而更强的模型则在更高计算成本下提供更鲁棒的推理。我们提出了AgentCollab,一种自我驱动的协作推理框架,能够在代理执行过程中动态协调不同推理能力的模型。该框架不依赖外部路由模块,而是利用代理自身的自我反思信号来判断当前推理轨迹是否在取得有意义进展,仅在必要时将控制权升级到更强的推理层级。为进一步稳定长周期执行,我们引入了基于难度的累积升级策略,根据最近的失败信号分配额外的推理预算。在实验中,我们使用双层级的小大模型设置实例化该框架。在多样化的多步骤代理基准测试中,AgentCollab一致地提升了LLM代理的准确性-效率帕累托前沿。

英文摘要:

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 https://github.com/SparkEngineAI/AgentFlashInfer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑