8 papers
"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…
MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning
Lingyan Wu, Xiang Zheng, Weiqi Zhai +5
Medical reasoning can reach a plausible answer while overlooking an unsafe or unsupported intermediate step. Process-Level Reward Models (PRMs) can verify such steps, yet existing…
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…
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…
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…
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5
Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat exec…
Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution
Shaobo Wang, Zhengbo Jiao, Zifan Zhang +6
Recent breakthroughs in large language models (LLMs) on reasoning tasks rely heavily on massive, high-quality datasets-typically human-annotated and thus difficult to scale. While…
SKYLENAGE Technical Report: Mathematical Reasoning and Contest-Innovation Benchmarks for Multi-Level Math Evaluation
Hu Wei, Ze Xu, Boyu Yang +15
Large language models (LLMs) now perform strongly on many public math suites, yet frontier separation within mathematics increasingly suffers from ceiling effects. We present two c…