FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
cs.LG, cs.SE
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Group-in-Group Policy Optimization for LLM Agent Training
- RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
- RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
- Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
- Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- Meta-RL Induces Exploration in Language Agents
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop
- CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
- ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- Self-Refine: Iterative Refinement with Self-Feedback
- Training Software Engineering Agents and Verifiers with SWE-Gym
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks