الباحثون

Xin Yin

المنشورات 2

نسخة أولية وصول مفتوح

Chronos Enables Code Agents to Reason over Software Evolution

Xin Yin, Yiang Zhang, Zhiyuan Peng وآخرون · 2026

Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experience relevant to a new task can span related changes whose descriptions emphasize different concerns. We introduce Chronos, a test-time framework that makes this connecte …

نسخة أولية وصول مفتوح

Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents

Boyang Yang, Zhenhao Li, Ziyao Yang وآخرون · 2026

Agents built on large language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call without notice. When the changed call fails, the agent retries a correct call, which costs users time and money. Benchmarks and failure analyses do not …

المؤلفون المشاركون