Entity · paper

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

paperactiveprovisionalllm-agents-for-deliberative-collaboration-a-study-on-joint-decision-making-under-partial-observability-1ac6bbba·1 events·first seen 8h ago

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

More like this (12)

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Always-OnAgents: A Survey of Persistent Memory, State, and Governance in LLM Agents Leadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in Multi-Agent LLM Teams human-LLM collaborative annotation Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?multi-agent cooperative framework Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats

Recent events (1)

5arXiv · cs.CL·8h ago·source ↗

Benchmark and study of LLM agents in deliberative multi-agent collaboration under partial observability

Researchers introduce a scalable benchmark for evaluating LLM agents on cooperative joint decision-making tasks where agents must exchange information under partial and asymmetric observations to reach a shared decision. A systematic evaluation of representative LLMs finds that state-of-the-art models still struggle with complex deliberative collaboration, failing in either information alignment or downstream reasoning even with external mathematical tools. Diagnostic analysis also reveals that deliberation can enable reflection and error correction, sometimes outperforming centralized baselines, offering a nuanced picture of multi-agent LLM capabilities.

Evaluation and Benchmarking Agent and Tool Ecosystem LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability