We have 6 of 13 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across long interactions. However, our diagnostic analysis shows that agents often fail to act on relevant information already available in context, while final Pass/Fail outc...
SWE-Nexus enables task construction from validated behavior beyond individual historical changes, a fully automated pipeline that constructs repository-level implementation tasks from test execution from test execution.
Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace...
TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable, and introduces TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-ad...
This work proposes Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill, and demonstrates transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers.
SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
