This work presents Caper, a consequence-aware approval mechanism that pre-executes each command in a snapshotted sandbox, provides an independent approver with a bounded report of its observed effects, commits allowed commands, and rolls back blocked ones with a reason the agent can act on.
Wei-Heng Wu, Junkai Chen, Zhensu Sun et al.· 0 citations
Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external knowledge bases also introduces new attack surfaces. Existing data extraction attacks against RAG systems rely on either prompt injection, which heavily depends on the generator...
Yuchen Chen, Wei Cheng, Yuan Xiao et al.· 0 citations
Large language models (LLMs) are increasingly used for code generation, yet generated programs may exhibit social bias through unfair or differential treatment of sensitive demographic attributes. While prior work mainly studies direct code generation, bias in reasoning-based generation remains underexplored. We conduc...
Wei-Feng Sun, Jie-Ke Shi, Zhou Yang et al.· 0 citations
Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate such healing code, but it is evaluated only on small competition programs, and executing LLM-generated code inside a live process raises safety concerns that remain unad...
Gou Tan, Peng-Fei Chen, Zhensu Sun et al.· arXiv.org· 0 citations
A typed domain-specific language that captures recurring tensor structures, such as repeated regions and floating-point fields, through a set of reversible operators, is designed, which formulates lossless tensor compression as program synthesis.
Jie-Ke Shi, Jun-Da He, Wenjia Jiang et al.· 0 citations
Evaluations across agent systems, benchmarks, and backbone LLMs under 65 fault configurations show that all systems degrade under fault injection, suggesting that robustness depends on system implementation rather than model capability.
Gou Tan, Zhensu Sun, Jie-Ke Shi et al.· Proceedings of the 41st IEEE...· 6 citations
Delta (Differential Testing for DRL Agents) is proposed, a novel and comprehensive framework that automatically identifies both safety-critical and optimality bugs in DRL agents and investigates the effectiveness of three offline RL algorithms in generating challenger agents.
Jun-Da He, Jie-Ke Shi, Zhou Yang et al.· Proceedings of the ACM on so...· 0 citations
Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limited in scale, domain coverage, or executable verification, leaving the true gap between current LLMs and reliable scientific code generators...
Weifeng Sun, Ye Fan, Yuchen Chen et al.· arXiv.org· 0 citations
This paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face, and describes a seven-stage workflow and five process shifts, including a move toward evaluation-driven development.
Yunbo Lyu, David Williams, Jieke Shi et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.