AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair

arXiv:2609.20130 · cs.SE, cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 12 pages, 9 figures

Code: https://github.com/Aider-AI/aider

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

Terminology

• Redundancy — 14× in this paper · explained in 2 episodes
• Quality-Aware Selection — 13× in this paper
• Coverage-Aware Retrieval — 12× in this paper
• Stage-Aware Routing — 11× in this paper
• Benchmark — 9× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Semantic Similarity — 3× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• In-Context Learning — 2× in this paper · explained in 4 episodes
• International Conference on Software Engineering — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Execution Success Rate — 1× in this paper
• Formal Verification — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Memory Augmentation — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends
• Evaluating Large Language Models Trained on Code
• Program Synthesis with Large Language Models
• Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
• Agentless: Demystifying LLM-based Software Engineering Agents
• PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
• MemGPT: Towards LLMs as Operating Systems
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• Retrieval-Augmented LLM Agents: Learning to Learn from Experience
• Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
• Retrieval-Augmented Generation for Large Language Models: A Survey
• SWE-Exp: Experience-Driven Software Issue Resolution
• Structurally Aligned Subtask-Level Memory for Software Engineering Agents
• REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement
• ReAct: Synergizing Reasoning and Acting in Language Models
• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
• Kimi K2.5: Visual Agentic Intelligence
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties