Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration
This addresses the need for more interpretable and robust reasoning in LLMs, though it is incremental as it builds on existing multi-agent and debate approaches.
The paper tackles the problem of LLMs lacking interpretable reasoning by introducing the Multi-Agent Collaboration Framework for Diverse Thinking Modes (DiMo), which simulates structured debates among specialized agents to improve accuracy and provide explicit reasoning chains, achieving the largest gains on math benchmarks.
Large Language Models (LLMs) demonstrate strong performance but often lack interpretable reasoning. This paper introduces the Multi-Agent Collaboration Framework for Diverse Thinking Modes (DiMo), which enhances both performance and interpretability by simulating a structured debate among four specialized LLM agents. Each agent embodies a distinct reasoning paradigm, allowing the framework to collaboratively explore diverse cognitive approaches. Through iterative debate, agents challenge and refine initial responses, yielding more robust conclusions and an explicit, auditable reasoning chain. Across six benchmarks and under a unified open-source setup, DiMo improves accuracy over widely used single-model and debate baselines, with the largest gains on math. We position DiMo as a semantics-aware, Web-native multi-agent framework: it models human-machine intelligence with LLM agents that produce semantically typed, URL-annotated evidence chains for explanations and user-friendly interactions. Although our experiments use standard reasoning benchmarks, the framework is designed to be instantiated over Web corpora and knowledge graphs, combining retrieval-augmented reasoning with structured justifications that downstream systems can inspect and reuse.