collaborators

10 papers

cs.LG2026

On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards

Fei Ding, Yongkang Zhang, Yuhao Liao +2

Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek…

cs.AI2026

ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning

Fei Ding, Yongkang Zhang, Runhao Liu +2

Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under…

cs.LG2026

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

Fei Ding, Yongkang Zhang, Youwei Wang +1

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment…

cs.LG2026

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

Fei Ding, Yongkang Zhang, Runhao Liu +4

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provid…

cs.LG2026

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

Fei Ding, Yongkang Zhang, Runhao Liu +5

This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomen…

cs.LG2026

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation

Fei Ding, Yongkang Zhang, youwei wang +1

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment…