collaborators

6 papers

cs.AI2026

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

Peng Kuang, Haibo Jin, Xiaoyu Han +5

Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent…

cs.AI2026

Closing the Loop on Latent Reasoning via Test-Time Reconstruction

Xiaopeng Yuan, Haibo Jin, Ye Yu +4

Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottlen…

cs.AI2026

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

Ye Yu, Heming Liu, Haibo Jin +3

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating i…

cs.CL2026

Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling

Peng Kuang, Yanli Wang, Xiaoyu Han +3

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise…

cs.CL2026

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations

Yanli Wang, Peng Kuang, Xiaoyu Han +2

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consisten…

cs.AI2025

TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM

Peng Kuang, Xiangxiang Wang, Wentao Liu +2

Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsiste…