papers

Publications (8)

cs.AI2026

CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning

Qixian Huang, Hongqiang Lin, Tong Fu +5

Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-s…

cs.AI2026

Offline Policy Optimization with Posterior Sampling

Hongqiang Lin, Dongxu Zhang, Yiding Sun +3

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distrib…

cs.AI2026

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Xiaofan Bai, Hongqiang Lin, Chao Liu +4

Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, example…

cs.AI2026

Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting

Hongqiang Lin, Chao Liu, Xiaofan Bai +4

The paper introduces SkillBoost, a three-stage framework that reduces overfitting of trainable skills in large language model agents by balancing constrained exploitation of failur…

#large language models#skill learning#exploration-exploitation#overfitting mitigation
cs.AI2026

Robust Regularized Policy Iteration under Transition Uncertainty

Hongqiang Lin, Zhenghui Fu, Weihao Tang +4

Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The lea…

cs.AI2026

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

Hongqiang Lin, Pengfei Wang, Nenggan Zheng

Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limite…

cs.CL2026

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Dongxu Zhang, Hongqiang Lin, Yiding Sun +4

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and in…

cs.CV2026

PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning

Dongxu Zhang, Yiding Sun, Pengcheng Li +12

While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…