SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at bug fixing, can they autonomously perform such migrations? Existing benchmarks cannot answer this question because they evaluate only behavioural correctness, not whether the migration actually occurred. This leads an easy hack: agents copy the original implementation to make tests pass. We call this Blindness. To address this problem, we introduce SWE Refactor Bench, a benchmark comprising 20 whole-repository migrati
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 26%SWE-agent/SWE-agent →
“Possibly related via embedding similarity 0.56 (not asserted). Timestamp check: artifact slightly before paper (-40d).”
- PossiblePossibly related (embedding) · 60%ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration →
- FuzzySimilar title/name (fuzzy) · 87%NirDiamant/GenAI_Agents →
“Fuzzy title match (0.94): “SWE Refactor Bench: Can Coding Agents Complete a Long-Horizo” ≈ “NirDiamant/GenAI_Agents””
- FuzzySimilar title/name (fuzzy) · 84%Unity-Technologies/ml-agents →
“Fuzzy title match (0.92): “SWE Refactor Bench: Can Coding Agents Complete a Long-Horizo” ≈ “Unity-Technologies/ml-agents””
- FuzzySimilar title/name (fuzzy) · 84%Thysrael/Horizon →
“Fuzzy title match (0.92): “SWE Refactor Bench: Can Coding Agents Complete a Long-Horizo” ≈ “Thysrael/Horizon””
- FuzzySimilar name plus overlapping authors · 67%TauricResearch/TradingAgents →
“Title similarity 0.73; shared authors: xiao”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”