2 papers
cs.SE2026
CoACT: Action-Preserving Observation Compression for Coding Agents
Haorui Chen, Yuancheng Zhu, Yitong Zhang +1
LLM-based coding agents solve software-engineering tasks through iterative interactions with development environments, where returned observations accumulate in the context and bec…
cs.CL2026
FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation
Haorui Chen, Chengze Li, Jia Li
Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully…