9 papers
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
Tingyu Li, Le Zhou, Siyuan Li +5
Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in comp…
Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
Zishang Jiang, Jinyi Han, Tingyun Li +7
Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effect…
From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
Zishang Jiang, Tingyun Li, Jinyi Han +7
Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face…
Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
Xinyi Wang, Jinyi Han, Zishang Jiang +7
Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods…
ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models
Tingyun Li, Zishang Jiang, Jinyi Han +8
Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-orient…
Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning
Tingyu Li, Zheng Sun, Jingxuan Wei +4
Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving lar…