As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought to increase task complexity through longer horizons and more extensive code modifications. However, real-world software development often spans multiple interdependent repositories, introducing additi...
Si-Lin Chen, Yu-Ling Shi, Heng Lian et al.· 0 citations
This work presents SpecBuild, an LLM-based environment setup system designed to be both faster and more successful through speculative forking, and demonstrates that parallel speculative exploration can make agents both faster and more successful.
Yu-Ling Shi, Ming-Chu Zhong, Zhensu Sun et al.· 1 citation
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an open-source framework for building, comparing, and extending these methods on shared infrastructure. Recipes compose reusabl...
Zi-Mu Wang, Xiaobo Wang, Si-Yu Ye et al.· 1 citation
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection a...
Hang He, Li-Sheng Wang, Hao Chen et al.· 3 citations
Datura, an automated red teaming testing framework that exposes safety vulnerabilities through chained tool manipulation, is proposed and evaluated across five LLMs and 740 safety-critical tasks under five defense settings, including real-world safety mechanisms.
Yu-Chen Shao, Zi-Qun Bao, Yu-Heng Huang et al.· Proceedings of the ACM on So...· 0 citations
EBM-RL (Eye--Brain--Mouth Reinforcement Learning), a decoupled GRPO-based framework that separates observation (), reasoning (), and utterance generation, mimics the human See-Think-Speak process, enabling the model to ground dialogue in visual perception before reasoning and response generation.
Miaosen Wang, Yu-Ling Shi, Yijiang Li et al.· arXiv.org· 0 citations
DLLM-Searcher is proposed, an optimization framework for dLLM-based Search Agents that designs a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning and Agentic Variance-Reduced Preference Optimization (Agentic VRPO), which enhances the backbone dLLM's information seeking and reasoning capabili...
Jiahao Zhao, Shaoxuan Xu, ZhongXiang Sun et al.· Annual International ACM SIG...· 0 citations
This work introduces early outcome prediction, a complementary axis of efficiency that instead cuts cost within each task within each task, and instantiates EarlyEval, a lightweight framework that trains a pair of LightGBM success and failure classifiers over behavioral, textual, and reference-solution features and hal...
This work identifies a phenomenon termed token-level memorization asymmetry through theoretical analysis of diffusion training dynamics and proposes Q-Skew, a quantile-weighted skewness-based indicator for membership inference on finetuned DLMs.
Sheng-Fang Zhai, Leo Marchyok, Yu-Ling Shi et al.· 1 citation· ⚡1
DeepRepoQA is proposed, a novel question answering (QA) framework for repository-level code understanding that builds on an agentic framework where LLM agents find answers through a systematic tree search over the repository structure.
Wei Peng, Yu-Ling Shi, Yingwei Ma et al.· 0 citations
LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understanding. Recent methods attempt to mitigate this limitation through pre-repair repository exploration; however, their fix-driven strategies expl...
ParaTempo is a training-free asynchronous parallel reasoning framework driven by temporal confidence, a branch-local measure of answer-space convergence that reduces average latency, and exhibits stronger temporal stability and predictive power for future branch convergence than token-level and instantaneous signals.
Xuteng Zhang, Wenhao Zeng, Xiao-Dong Gu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.