Improving Large Language Models for Code through Runtime Program-State Reasoning
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/SWE-agent/mini-swe-agent
Sources
- Chain of Execution Supervision Promotes General Reasoning in Large Language Models
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- TACO: Topics in Algorithmic COde generation dataset
- Competition-Level Code Generation with AlphaCode
- Self-Execution Simulation Improves Coding Models
- SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
- Training Software Engineering Agents and Verifiers with SWE-Gym
- Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
- CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
- StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
- SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
- SWE-smith: Scaling Data for Software Engineering Agents
- Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
- Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems