FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents
Dongyi Lv, Fushun E, Aichen Cai, Liang Huang, Ya Zhang, Qiuyu Ding, Canhui Wu, Zhi Wang, Yuesong Zhang, Jiaqi Wang, Nan Duan
cs.AI
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Reinforced Self-Training (ReST) for Language Modeling
- AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
- Exploring Expert Failures Improves LLM Agent Tuning
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Training Software Engineering Agents and Verifiers with SWE-Gym
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Step Rejection Fine-Tuning: A Practical Distillation Recipe
- Hindsight Credit Assignment for Long-Horizon LLM Agents
- Kimi K2.5: Visual Agentic Intelligence
- Kimi K2: Open Agentic Intelligence
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
- Agent Workflow Memory
- Learn Hard Problems During RL with Reference Guided Fine-tuning
- Agentless: Demystifying LLM-based Software Engineering Agents
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
- GLM-5: from Vibe Coding to Agentic Engineering
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