AIToday
Large Language ModelsarXiv cs.MA (Multi-Agent)Published: Apr 28, 2026, 13:00 JST

Researchers propose Decision Language Model (DLM) for multi-agent offline decision-making, formulating the task as dialogue-style sequence prediction

Send on LINE

3 Key Points

  1. DLM trains in two stages: supervised fine-tuning on dialogue-style datasets for centralized training with inter-agent context, followed by group relative policy optimization to enhance robustness to out-of-distribution actions through lightweight reward functions.

  2. Unlike existing offline multi-agent reinforcement learning methods that rely on fixed observation formats and action spaces, DLM leverages the flexible modeling interface of large language models (LLMs) to accommodate heterogeneous observations and actions across agents.

  3. Experiments show DLM outperforms strong offline MARL baselines and LLM-based conversational decision-making methods, while demonstrating strong zero-shot generalization to unseen scenarios across tasks.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

arXiv cs.MA (Multi-Agent)Read Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleDualOpt: A decoupled optimization approach tailored separately for training neural networks from scratch and fine-tuning pre-trained models