MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability

2026-01-14

AI Summary

This work addresses the challenge of inefficient coordination among spatially distributed large language model agents operating under spatiotemporal partial observability. To this end, the authors propose a novel multi-agent collaborative reasoning framework that integrates predictive backtracking, mean-field negotiation, and semantic gradient introspection. The architecture comprises three core modules—CoProposer, Negotiator, and Introspector—unifying predictive verification, statistical aggregation, and semantic gradient descent within a single framework for the first time in spatiotemporal multi-agent coordination tasks. Experimental results demonstrate that the proposed method significantly enhances coordination performance in real-world scenarios such as cooperative adaptive cruise control and epidemic response management, effectively mitigating the limitations imposed by local observability.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Large Language Model (LLM) agents deployed in complex real-world scenarios typically operate as spatially distributed entities. However, this physical dispersion constrains agents to limited local perception and finite temporal horizons. We characterize this bottleneck as spatiotemporal partial observability. Given such fragmented awareness, distributed agents struggle to coordinate efficiently. To bridge this gap, we introduce MACRO-LLM, LLM-empowered multi-agent collaborative reasoning under spatiotemporal partial observability. The architecture addresses spatiotemporal constraints via three modules: (1) the CoProposer mitigates temporal uncertainty by verifying candidate actions via predictive rollouts; (2) the Negotiator overcomes spatial myopia by resolving conflicts through mean-field statistical aggregation; and (3) the Introspector ensures continuous adaptation by analyzing historical experience to refine strategies via semantic gradient descent. Extensive evaluations on two complex long-horizon tasks, cooperative adaptive cruise control and pandemic control, demonstrate that our framework effectively mitigates spatiotemporal partial observability through spatial and temporal strategies, enabling robust coordination.

Problem

• spatiotemporal partial observability
• multi-agent coordination
• distributed LLM agents
• limited local perception
• finite temporal horizons

Innovation

• spatiotemporal partial observability
• multi-agent collaborative reasoning
• large language models
• mean-field aggregation
• semantic gradient descent