2 citations · 3 across the 7 of their papers we have counts for
4 papers · 1 filter
Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents
Haobin Li, Liang Jiang, Zhenyu Huang +2
Recently, coding agents have emerged as a dominant paradigm for real-world software engineering (SWE) scenarios, which solve complex tasks through multi-turn interactions with deve…
Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports
Haobin Li, Ping Deng, Weizhong Qian +4
Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase. Ho…
Reliable Thinking with Images
Haobin Li, Yutong Yang, Yijie Lin +3
As a multimodal extension of Chain-of-Thought (CoT), Thinking with Images (TWI) has recently emerged as a promising avenue to enhance the reasoning capability of Multi-modal Large…
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
Yijie Lin, Guofeng Ding, Haochen Zhou +3
Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To…