4 papers
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
Jingzhe Ding, Shengda Long, Changxin Pu +46
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities re…
How Far Are We from Genuinely Useful Deep Research Agents?
Dingling Zhang, He Zhu, Jincheng Ren +15
Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRAs were validated on…
IF-VidCap: Can Video Caption Models Follow Instructions?
Shihao Li, Yuanxing Zhang, Jiangtao Wu +20
Although Multimodal Large Language Models (MLLMs) have demonstrated proficiency in video captioning, practical applications require captions that follow specific user instructions…
HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs
Ken Deng, Zizheng Zhan, Wen Xiang +25
Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inef…