collaborators

5 papers

cs.LG2026

Self-Supervised On-Policy Distillation for Reasoning Language Models

Zhiquan Tan, Yinrong Hong

GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We show that a mixed group con…

cs.LG2026

PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners

Zhiquan Tan, Yinrong Hong

Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement lea…

cs.LG2026

From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents

Shuoling Liu, Zhiquan Tan, Kun Yi +6

Deep Research Agents (DRAs) aim to answer complex questions by searching the web, checking evidence, and synthesizing conclusions across heterogeneous sources. We introduce a categ…

cs.CL2026

Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models

Yinrong Hong, Zhiquan Tan, Kai Hu

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges a…

cs.LG2025

A Theoretical Lens for RL-Tuned Language Models via Energy-Based Models

Zhiquan Tan, Yinrong Hong

Large language models (LLMs) trained via KL-regularized reinforcement learning demonstrate strong instruction following, self-correction, and reasoning abilities. Yet their theoret…