LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

2026-07-07

AI Summary

This work addresses the challenge of multi-agent negotiation and collaboration in partially observable environments with asymmetric observations, where current large language models (LLMs) exhibit limited performance. The study formalizes negotiation-based collaboration as a joint decision-making problem, introduces a cross-domain and scalable evaluation benchmark, and systematically assesses LLMs’ capabilities in tasks requiring information exchange to achieve shared rewards. By designing negotiation protocols, integrating external tools, and explicitly modeling partial observability, the research reveals significant shortcomings of LLMs in negotiation alignment and complex reasoning. Nevertheless, it also uncovers that negotiation mechanisms possess reflective and error-correction potential, which, in certain scenarios, can enhance performance—even surpassing centralized baselines.

Abstract

Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach an agreement. In this paper, we investigate deliberative large language model (LLM) agents under partially observable joint decision-making tasks. We formalize deliberative collaboration as a cooperative joint decision problem with partial and asymmetric observations, and introduce a scalable benchmark that instantiates this problem across multiple task settings and domains in which agents must exchange information through deliberation to reach a joint decision with a shared reward. We then instantiate a reference scaffold and evaluation protocol for deliberative agents and conduct a systematic evaluation of a range of representative LLMs. The results reveal that complex deliberative collaboration tasks continue to challenge state-of-the-art language models. Even with the aid of external mathematical tools, language models may fail in either the deliberation process for aligning information or the complex reasoning process for making the decision. On the other hand, diagnostic analysis reveals that the deliberation process may also provide opportunities for reflection and error correction, sometimes improving performance over centralized baselines. Altogether, our work establishes a foundation for evaluating and improving LLM agents in deliberative collaboration and provides insights into the strengths, limitations, and properties of current LLM-based multi-agent systems.

Problem

• deliberative collaboration
• partial observability
• joint decision making
• LLM agents
• multi-agent systems

Innovation

• deliberative collaboration
• partial observability
• LLM agents
• joint decision making
• multi-agent evaluation