Skip to content

Accepted to NeurIPS 2026 #84

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
langfengQ merged 1 commit into from
Sep 26, 2026
Merged

Accepted to NeurIPS 2026 #84

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 22 additions & 8 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,14 @@
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
</h1>

<h3 align="center">
<strong>NeurIPS 2026</strong><br>
MALGAI @ ICLR 2026
</h3>

<p align="center">
<a href="https://langfengq.github.io/DrMAS/">
<img src="https://img.shields.io/badge/Project-Page-8C569B" alt="Project Page">
<img src="https://img.shields.io/badge/Project-Website-8C569B" alt="Project Website">
</a>
<a href="https://arxiv.org/abs/2602.08847">
<img src="https://img.shields.io/static/v1?label=arXiv&message=Paper&color=red" alt="arXiv Paper">
Expand All @@ -25,22 +30,31 @@ Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
<a href="https://github.com/langfengQ/DrMAS/blob/master/LICENSE">
<img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License">
</a>
<!-- <a href="https://github.com/langfengQ/DrMAS/issues">
<img src="https://img.shields.io/github/issues/langfengQ/DrMAS" alt="GitHub issues">
</a> -->
<a href="https://github.com/langfengQ/DrMAS/stargazers">
<img src="https://img.shields.io/github/stars/langfengQ/DrMAS?style=social" alt="Repo stars">
</a>
</p>

The project-page source and visual previews are available in [website/](./website/README.md).
**News:** 🎉 Dr. MAS has been accepted to **NeurIPS 2026!**

Dr. MAS is designed for **end-to-end post-training** of **Multi-Agent LLM Systems** via **Reinforcement Learning (RL)**, enabling multiple LLM-based agents to collaborate on complex reasoning and decision-making tasks.

`Dr.MAS` is designed for **end-to-end post-training** of **Multi-Agent LLM Systems** via **Reinforcement Learning (RL)**, enabling multiple LLM-based agents to collaborate on complex reasoning and decision-making tasks.
<p align="center">
<a href="./docs/drmas/drmas_overview.png">
<img src="./docs/drmas/drmas_overview.png" alt="Figure 1: Dr. MAS uses agent-wise advantage normalization for stable reinforcement learning and supports co-training multiple LLM actors." width="100%">
</a>
<br>
<em>Figure 1. Agent-wise normalization for stable multi-LLM RL.</em>
</p>

This framework features **flexible agent registry**, **customizable multi-agent orchestration**, **LLM sharing/non-sharing (e.g., heterogeneous LLMs)**, **per-agent configuration**, and **shared resource pooling**, making it well suited for training multi-agent LLM systems with RL.

<p align="center">
<img src="./docs/drmas/drmas_framework.png" alt="framework" width="100%">
<a href="./docs/drmas/drmas_framework.png">
<img src="./docs/drmas/drmas_framework.png" alt="Figure 2: The Dr. MAS framework connects environment workers, multi-agent orchestration, agent-model assignment, shared GPU scheduling, and per-worker-group optimization." width="100%">
</a>
<br>
<em>Figure 2. The Dr. MAS framework for end-to-end multi-agent LLM RL.</em>
</p>

# Feature Summary
Expand All @@ -54,7 +68,7 @@ This framework features **flexible agent registry**, **customizable multi-agent
| **Shared Resource Pooling** | ✅ Shared GPU pool across multiple LLM worker groups for efficient hardware utilization<br>✅ Gradient updates applied independently for each worker group during optimization |
| **Environments** | ✅ Math<br>✅ Search |
| **Model Support** | ✅ Qwen2.5<br>✅ Qwen3<br>✅ LLaMA3.2<br>and more |
| **RL Algorithms** | ✅ Dr.MAS<br>✅ GRPO<br>🧪 GiGPO (experimental)<br>🧪 DAPO (experimental) <br>🧪 RLOO (experimental) <br>🧪 PPO (experimental) <br>and more |
| **RL Algorithms** | ✅ Dr. MAS<br>✅ GRPO<br>✅ GiGPO<br>✅ DAPO <br>✅ RLOO <br>✅ PPO <br>and more |

# Table of Contents

Expand Down
Binary file modified docs/drmas/drmas_framework.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/drmas/drmas_overview.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
5 changes: 4 additions & 1 deletion website/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,10 @@
<div class="container hero-content">
<div class="hero-topline"><span class="eyebrow hero-eyebrow">Multi-agent reinforcement learning</span></div>
<h1 id="paper-title"><span class="hero-name">Dr. MAS</span><span class="hero-title">Stable Reinforcement Learning<br class="desktop-break" /> for Multi-Agent LLM Systems</span></h1>
<p class="hero-description"><span class="venue-badge">NeurIPS 2026</span></p>
<p class="hero-description">
<span class="venue-badge">NeurIPS 2026</span>
<span class="venue-badge venue-workshop">MALGAI @ ICLR 2026</span>
</p>
<div class="authors" aria-label="Paper authors">
<a href="https://langfengq.github.io/" target="_blank" rel="noopener noreferrer">Lang Feng</a>
<a href="https://ltzheng.github.io/" target="_blank" rel="noopener noreferrer">Longtao Zheng</a>
Expand Down
5 changes: 3 additions & 2 deletions website/src/styles.css
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,12 +98,13 @@ sup { font-size: .55em; }
.hero::before { content: ''; position: absolute; z-index: -1; width: 900px; max-width: 100%; height: 550px; top: 0; left: 50%; transform: translateX(-50%); background: radial-gradient(ellipse at 50% 0, #ebdfef9c, transparent 70%); pointer-events: none; }
.hero-content { text-align: center; }
.hero-topline { display: flex; flex-wrap: wrap; align-items: center; justify-content: center; gap: 12px; }
.venue-badge { display: inline-flex; align-items: center; color: var(--accent-strong); border: 1px solid #cdb9d6; background: #f3edf6; padding: 5px 10px; font: 14px var(--mono); border-radius: 4px; letter-spacing: .035em; }
.venue-badge { display: inline-flex; align-items: center; color: var(--accent-strong); border: 1px solid #cdb9d6; background: #f3edf6; padding: 5px 10px; font: 14px var(--mono); border-radius: 4px; letter-spacing: .035em; white-space: nowrap; }
.venue-workshop { color: var(--muted); border-color: var(--line); background: transparent; }
.hero-eyebrow { display: inline-flex; gap: 10px; align-items: center; color: #7d6686; font-size: 10px; letter-spacing: .11em; }
.hero h1 { margin-top: 18px; }
.hero-name { display: block; font-size: clamp(48px, 5vw, 64px); font-weight: 600; letter-spacing: -.055em; line-height: 1.1; color: var(--accent); }
.hero-title { display: block; font-size: clamp(26px, 3.2vw, 42px); letter-spacing: -.04em; line-height: 1.22; margin-top: 12px; font-weight: 500; }
.hero-description { color: var(--muted); font-size: 15px; margin-top: 18px; }
.hero-description { display: flex; flex-wrap: wrap; align-items: center; justify-content: center; gap: 8px; color: var(--muted); font-size: 15px; margin-top: 18px; }
.authors { display: flex; align-items: center; justify-content: center; flex-wrap: wrap; gap: 8px 23px; margin-top: 23px; font-size: 15px; font-weight: 500; }
.authors a { text-decoration-color: var(--line); text-decoration-line: underline; text-underline-offset: 4px; }
.authors a:hover { color: var(--accent); text-decoration-color: var(--accent); }
Expand Down
Loading