3 papers
cs.AI2026
RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding
Jingxuan Xu, Zihang Xu, Yuechen Luo +9
Long-horizon coding agents can observe a failure and generate a plausible critique yet continue along the same incorrect trajectory. We call this the Critique-to-Action Handoff Gap…
cs.SE2026
SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution
Songwei Yu, Ziqi Miao, Jingxuan Xu +10
Historical code changes provide convenient task boundaries, but do not identify which production functions selected tests exercise or support composing validated behaviors beyond a…
cs.SE2026
TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry
Yujia Luo, Haonan Zhang, Jiasi Shen +2
Large language models can generate runnable web applications from natural-language requirements, but many generated applications still fail interactive tasks. Existing generate-exe…