12 papers
HSD: Hybrid Hindsight Self-Distillation
Qiye Cai, Yichuan Ma, Peiji Li +6
Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning, but a scalar trajectory reward offers limited token-level…
Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
Xiaozhe Li, Yang Li, Xinyu Fang +10
On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once disc…
What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
Xiaozhe Li, Tianyi Lyu, Yang Li +6
Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed…
Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic
Yichuan Ma, Linyang Li, Yongkang chen +5
As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with fr…
TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization
Peiji Li, Linyang Li, Handa Sun +15
Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimize…
Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go
Yichuan Ma, Linyang Li, Yongkang Chen +5
Large language models (LLMs) have demonstrated exceptional performance in reasoning tasks such as mathematics and coding, matching or surpassing human capabilities. However, these…