Software Engineering Agents
Overview
Software engineering agents use language models to work on tasks such as fixing repository issues, writing tests, building projects, reviewing code, and modernizing software. Common approaches combine planning and code retrieval with tools that run builds and tests; other systems use multiple specialized agents, repository memory, reinforcement learning, or formal verification. Performance is often evaluated on repository-level benchmarks such as SWE-bench, alongside terminal tasks and real-world settings that test build success, design constraints, and behavior over multiple steps. Agents can solve many tasks, but dependable performance remains difficult: passing tests may not mean a patch follows project intent, and greater autonomy or more agents can increase cost, regressions, and oversight demands.
Latest papers
349 papers71 papers in the last four weeks, up 103% on the four weeks before. 0.4% of all new papers.