collaborators

6 papers

cs.LG2026

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Wanghan Xu, Shuo Li, Tianlin Ye +48

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchma…

cs.SE2026

Dockerless: Environment-Free Program Verifier for Coding Agents

Wenhao Zeng, Yuling Shi, Xiaodong Gu +10

Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning…

cs.SE2026

In Line with Context: Repository-Level Code Generation via Context Inlining

Chao Hu, Wenhao Zeng, Yuling Shi +2

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository,…

cs.AI2026

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

Wenhao Zeng, Xuteng Zhang, Yuling Shi +4

Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and com…

cs.CV2026

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction

Zichun Guo, Yuling Shi, Wenhao Zeng +6

Multimodal Large Language Models (MLLMs) have achieved remarkable performance in Visually Rich Document Understanding (VRDU) tasks, but their capabilities are mainly evaluated on p…

cs.LG2026

Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal

Wenhao Zeng, Yaoning Wang, Chao Hu +4

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities by scaling up the length of Chain-of-Thought (CoT). However, excessively long reasoning traces pose substant…