Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gao, Wenbo, Liu, Renxi, Wang, Xian, Guo, Fang, Yang, Shuai, Chen, Xi, Zhen, Hui-Ling, Chen, Hanting, Lin, Weizhe, Li, Xiaosong, Wang, Yaoyuan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.26034
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912984873304064
author Gao, Wenbo
Liu, Renxi
Wang, Xian
Guo, Fang
Yang, Shuai
Chen, Xi
Zhen, Hui-Ling
Chen, Hanting
Lin, Weizhe
Li, Xiaosong
Wang, Yaoyuan
author_facet Gao, Wenbo
Liu, Renxi
Wang, Xian
Guo, Fang
Yang, Shuai
Chen, Xi
Zhen, Hui-Ling
Chen, Hanting
Lin, Weizhe
Li, Xiaosong
Wang, Yaoyuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26034
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
Gao, Wenbo
Liu, Renxi
Wang, Xian
Guo, Fang
Yang, Shuai
Chen, Xi
Zhen, Hui-Ling
Chen, Hanting
Lin, Weizhe
Li, Xiaosong
Wang, Yaoyuan
Computation and Language
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.
title AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
topic Computation and Language
url https://arxiv.org/abs/2603.26034