Papers
arxiv:2511.20468

DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs

Published on Nov 25
Authors:
,
,
,
,
,

Abstract

DRAFT-RL integrates Chain-of-Draft reasoning into multi-agent RL to enhance exploration, peer reflection, and reward alignment, improving LLM performance in complex reasoning tasks.

AI-generated summary

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using reinforcement learning (RL). However, these approaches often rely on single-shot responses and lack structural diversity in reasoning exploration. In this paper, we propose DRAFT-RL, a novel framework that integrates Chain-of-Draft (CoD) reasoning into multi-agent RL training. Instead of generating single responses, each agent produces multiple drafts per query, which are then evaluated by peer agents and a learned reward model to identify the most promising trajectory. These selected drafts are used to refine future reasoning strategies through actor-critic learning.DRAFT-RL enables explicit multi-path exploration, peer-guided reflection, and reward-aligned selection, resulting in more robust and interpretable LLM agent behavior. We evaluate our method on complex reasoning tasks including code synthesis, symbolic math, and knowledge-intensive QA,demonstrating that DRAFT-RL outperforms existing reflective and RL-based agents by significant margins in both accuracy and convergence speed

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2511.20468 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2511.20468 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.20468 in a Space README.md to link it from this page.

Collections including this paper 1