AI Paper Atlas

Research map / Large language models / Agents, code and math

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Xiang Deng, Jeff Da, Edwin Pan, Yannis Yiming He, Charles Ide, Kanak Garg, Niklas Lauffer, Andrew Park, Chetan Rane, Karmini Sampath, Maya Krishnan, Srivatsa R Kundurthy and 6 more

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add human-written requirements and interface to the problem statement (ablation)GPT-5 (high) · SWE-Bench Pro publicresolve rate (%): 8.40% -> 25.9%Improved
add human-written requirements and interface to the problem statement (ablation)Claude Opus 4.1 · SWE-Bench Pro publicresolve rate (%): 8.20% -> 22.7%Improved
use commercial (private startup) repositories instead of public copyleft repositoriesBest models · SWE-Bench Pro commercial vs publicresolve rate (%): 25.9 -> 15.7 (GPT-5 high); 22.7 -> 17.8 (Claude Opus 4.1)Hurt
use Agentless scaffold instead of SWE-AgentSWE-Bench Pro evaluation · SWE-Bench Proresolve rateHurt
increase number of files edited in the reference patchAll models · SWE-Bench Pro publicresolve rate (%)Hurt
use frontier models instead of open-weight models on 10+ file problemsClaude Opus 4.1, GPT-5 · SWE-Bench Pro public, 10+ filesresolve rate (%): above 10% vs near-zeroImproved
use Go or Python instead of JavaScript or TypeScript tasksAll models · SWE-Bench Pro public by languageresolve rate (%)Mixed
judge on last 20 turns of trajectories rather than 10 or 40 (ablation)LLM-as-judge failure analysis · Failure-mode classificationagreement with human validationImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy