EUVIMEDEUVIMED entdecken
Crossref

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

Yuanhao Li, Mingshan Liu, Hongbo Wang, Yiding Zhang, Yifei Ma, Wei Tan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29530-29537

DOI: 10.1609/aaai.v40i35.40195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuanhao Li und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Li, Y., Liu, M., Wang, H., Zhang, Y., Ma, Y., & Tan, W. (2026). DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29530-29537. https://doi.org/10.1609/aaai.v40i35.40195

Vancouver

Li Y, Liu M, Wang H, Zhang Y, Ma Y, Tan W. DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29530-29537. doi:10.1609/aaai.v40i35.40195

BibTeX
@article{Li2026,
  author = {Li, Yuanhao and Liu, Mingshan and Wang, Hongbo and Zhang, Yiding and Ma, Yifei and Tan, Wei},
  title = {DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29530--29537},
  doi = {10.1609/aaai.v40i35.40195}
}
Kostenlos starten →