Teaching Agents to Code Reliably

cs.AI, cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: Submitted to ICLR 2027

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Investigating Test Overfitting on SWE-bench
• TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
• SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
• Ockhamareto: Pareto-Gated Segment-Level Credit Assignment for Concise Unit-Test Generation with Reinforcement Learning
• R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
• Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
• SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
• Training Software Engineering Agents and Verifiers with SWE-Gym
• Agentic Rubrics as Contextual Verifiers for SWE Agents
• SWE-RM: Execution-free Feedback For Software Engineering Agents
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes
• SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
• Agentless: Demystifying LLM-based Software Engineering Agents

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