arXiv cs.CL· Matthew Groholski, Weiwei Gu, Nakul Gopalan·· 23 小时前AI 评分24
对话驱动的动态任务分配:通信增强贝叶斯框架提升部分可观测下的多智能体协作效率
Dynamic Task Allocation with Dialogue
AI 导读
研究者提出一种通信增强的贝叶斯任务分配框架,让智能体通过对话降低对环境和协作者的不确定性,并将决策建立在显式概率信念之上。在扩展了动态到达任务的 Overcooked 环境中,该通信智能体在全观测和部分观测下均稳定优于普通 LLM 智能体。部分观测且任务复杂度上升时,它比非通信基线平均快 0.585、平均提前 18 个时间步完成任务。
正文 · 原文
Abstract:Effective multi-agent collaboration requires agents to adapt task allocation as goals and responsibilities evolve. Prior task-allocation frameworks often assume static goals, full observability, or rely on large language models (LLMs) without explicit, verifiable beliefs about task allocation or intent. These assumptions limit their applicability to real-world collaboration, where agents often lack full information about each other's actions, progress, or local environment. To support dynamic task allocation under partial observability, we introduce a communication-augmented Bayesian task-allocation framework. Our agent uses dialogue to reduce uncertainty about the environment and collaborators, while keeping decisions grounded in explicit probabilistic beliefs. We evaluate our framework in an Overcooked domain extended with dynamically arriving tasks under both full and partial object-space observability. Our communication agent consistently outperforms a vanilla LLM agent in both settings. Additionally, our framework performs comparably to a non-communicating task-allocation baseline under full observability, but substantially outperforms it under partial observability as task complexity increases by an average speed up of 0.585 and completes on average 18 timesteps faster. These results indicate that our agent is more efficient in dynamic task allocation than baselines in partially observable environments, and that communication is important as available information decreases.
| Comments: | 9 pages, 6 figures, Accepted at Human-Robot Dialogue(HRD) Workshop at IROS 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.23119 [cs.CL] |
| (or arXiv:2611.23119v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23119 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Weiwei Gu [view email]
[v1]
Tue, 17 Nov 2026 17:37:17 UTC (1,204 KB)
来源:arXiv cs.CL · arxiv.org