cs.CLNov 17, 2026

Dynamic Task Allocation with Dialogue

Authors: Matthew Groholski, Weiwei Gu, Nakul Gopalan

Organizations: School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA

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.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Goal-Aware Dynamic Multi-Agent Collaboration for Long-Horizon Tasks

    Oct 29, 2026Xu Shen, Lingyong Yan, Shuaiqiang Wang +4Multi-Agent LLM SystemsLong-Horizon Agent Tasks

  2. MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability

    Oct 3, 2026Qizhi Chu, Zekai Yu, Sijie Wen +5Multi-Agent LLM SystemsMulti-Agent Collaboration