Papers › Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning

Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning

16 Jun 2025arXiv:2506.13056archive 2025-07-28

Haibo Qiu, Xiaohan Lan, Fanfan Liu, Xiaohu Sun, Delian Ruan, Peng Shi, Lin Ma

Recent advancements in large language models (LLMs) have witnessed a surge in the development of advanced reasoning paradigms, which are now being integrated into multimodal large language models (MLLMs). However, existing approaches often fall short: methods solely employing reinforcement learning (RL) can struggle with sample inefficiency and activating entirely absent reasoning capabilities, while conventional pipelines that initiate with a cold-start supervised fine-tuning (SFT) phase before RL may restrict the model's exploratory capacity and face suboptimal convergence. In this work, we introduce \textbf{Metis-RISE} (\textbf{R}L \textbf{I}ncentivizes and \textbf{S}FT \textbf{E}nhances) for multimodal reasoning model learning. Unlike conventional approaches, Metis-RISE distinctively omits an initial SFT stage, beginning instead with an RL phase (e.g., using a Group Relative Policy Optimization variant) to incentivize and activate the model's latent reasoning capacity. Subsequently, the targeted SFT stage addresses two key challenges identified during RL: (1) \textit{inefficient trajectory sampling} for tasks where the model possesses but inconsistently applies correct reasoning, which we tackle using self-distilled reasoning trajectories from the RL model itself; and (2) \textit{fundamental capability absence}, which we address by injecting expert-augmented knowledge for prompts where the model entirely fails. This strategic application of RL for incentivization followed by SFT for enhancement forms the core of Metis-RISE, leading to two versions of our MLLMs (7B and 72B parameters). Evaluations on the OpenCompass Multimodal Reasoning Leaderboard demonstrate that both models achieve state-of-the-art performance among similar-sized models, with the 72B version ranking fourth overall. Please refer to our project page for open-source information.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mm-thinking/metis-rise officialmentioned in papermentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multimodal ReasoningReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SFT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections