OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908604292923392 |
|---|---|
| author | Bi, Zhenyu Lu, Meng Li, Yang Roy, Swastik Guan, Weijie Ziyadi, Morteza Wang, Xuan |
| author_facet | Bi, Zhenyu Lu, Meng Li, Yang Roy, Swastik Guan, Weijie Ziyadi, Morteza Wang, Xuan |
| contents | Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents. However, existing collaboration structures are either predefined or rely on majority voting or round-table debates, which can suppress correct but less dominant agent contributions. Recent approaches model multi-agent systems as graph networks but optimize purely for agent performance, neglecting the quality of interactions. We hypothesize that effective agent communication is crucial for multi-agent reasoning and that debating quality plays a significant role. To address this, we propose $\ours$, a multi-agent verbal reinforcement learning algorithm that dynamically constructs and refines multi-agent collaboration structures. Our method defines action spaces and a feedback mechanism that evaluates communication robustness and coherence throughout the debate. The final decision is achieved through a majority vote over all the agents. We assess $\ours$ on various reasoning tasks, including mathematical reasoning, creative writing, scientific reasoning, and numerical sorting. Results demonstrate that our approach significantly outperforms single-agent prompting methods and state-of-the-art multi-agent frameworks on diverse tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18032 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning Bi, Zhenyu Lu, Meng Li, Yang Roy, Swastik Guan, Weijie Ziyadi, Morteza Wang, Xuan Artificial Intelligence Multiagent Systems Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents. However, existing collaboration structures are either predefined or rely on majority voting or round-table debates, which can suppress correct but less dominant agent contributions. Recent approaches model multi-agent systems as graph networks but optimize purely for agent performance, neglecting the quality of interactions. We hypothesize that effective agent communication is crucial for multi-agent reasoning and that debating quality plays a significant role. To address this, we propose $\ours$, a multi-agent verbal reinforcement learning algorithm that dynamically constructs and refines multi-agent collaboration structures. Our method defines action spaces and a feedback mechanism that evaluates communication robustness and coherence throughout the debate. The final decision is achieved through a majority vote over all the agents. We assess $\ours$ on various reasoning tasks, including mathematical reasoning, creative writing, scientific reasoning, and numerical sorting. Results demonstrate that our approach significantly outperforms single-agent prompting methods and state-of-the-art multi-agent frameworks on diverse tasks. |
| title | OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2510.18032 |