works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.AI2026

Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution

Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5

The paper introduces Policy of Thoughts (PoT), a test‑time training framework that continuously updates a lightweight LoRA adapter using online policy optimization to improve large…

cs.SE2026

"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution

Zhao Tian, Zifan Zhang, Tao Xiao +4

Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which hu…

cs.CL2026

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

Lingyan Wu, Xiang Zheng, Weiqi Zhai +5

Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general domains such as mathematics,…

cs.AI2026

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

Zhengbo Jiao, Shaobo Wang, Zifan Zhang +4

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet how visual evidence is…

cs.CV2026

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

Zhengbo Jiao, Shaobo Wang, Zifan Zhang +4

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, reveali…

cs.AI2026

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

Zhengbo Jiao, Shaobo Wang, Zifan Zhang +5

Advancing complex reasoning in large language models relies on high-quality, verifiable datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synt…