14 papers
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
Ruoyu Wang, Jierun Chen, Shaowei Wang +7
Coding agents increasingly generate pull requests (PRs) for real-world software issues, yet one-shot PR generation remains open-loop: the PR is proposed without systematic review,…
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Sidi Yang, Chaofan Tao, Jierun Chen +11
Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and stude…
Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation
Shutian Gu, Chengkai Huang, Ruoyu Wang +1
Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments. Recent approaches increasingly e…
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
Junda Wu, Yuxin Xiong, Xintong Li +9
Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive r…
SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
Chaofan Tao, Jierun Chen, Yuxin Jiang +11
We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent m…
DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer
Ruoyu Wang, Junda Wu, Yu Xia +4
Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks. However, existing works ha…