Agents & Tool Use · 2024
SWE-agent / OpenHands (autonomous software engineering)
They packaged a language model as an autonomous agent with a structured interface to a code repository, shell, and editor, showing that a model given the right tools and feedback loop can resolve real GitHub issues end to end rather than only generating isolated code snippets.
Editorial record
Plain-language summary
These systems give the model a defined set of actions for navigating files, editing code, and running commands, plus the feedback it gets back from executing those actions, so it can work through a real bug or feature request over many steps. On the SWE-bench benchmark of actual GitHub issues, this agent-plus-tools approach resolved a meaningful fraction of tasks that require reading a codebase, making changes, and checking them. The work showed that the design of the agent's action interface, not just the underlying model, strongly affects how many software tasks get solved, and the released open frameworks made this style of coding agent broadly available.
Knowledge graph
Relationships
Descendants
CombinesEvidence: Strongly supported
Voyager / Generative Agents
Memory/skill-library ideas feed coding agents
P-235
CombinesEvidence: Strongly supported
Reflexion: Language Agents with Verbal Reinforcement Learning
Self-reflection feeds SWE agents
P-235
Applies toEvidence: Strongly supported
DeepSeek-R1: Incentivizing Reasoning via RL (RLVR)
Verifiable-reward logic applies to SWE-bench-graded agents
P-235
Source record
Provenance
- Record ID
- P-235
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2405.15793
- arXiv:2405.15793
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.