SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2representative citing papers
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
citing papers explorer
-
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
-
Rethinking Code Performance Benchmarks for LLMs
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.