# TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code arXiv: https://arxiv.org/abs/2602.06875 ยท HTML: https://mlsanity.com/paper/2602.06875/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 31 of its 53 references that are in the map. - First posted on arXiv 6 Feb 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 30 of 31) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024) - [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023) - [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023) - [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023) - [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023) - [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023) - [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024) - [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023) - [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023) - [DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models](https://mlsanity.com/paper/2410.07331/) (2024) - [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023) - [AutoVerus: Automated Proof Generation for Rust Code](https://mlsanity.com/paper/2409.13082/) (2024) - [A Deep Dive into Large Language Models for Automated Bug Localization and Repair](https://mlsanity.com/paper/2404.11595/) (2024) - [Agent-Oriented Planning in Multi-Agent Systems](https://mlsanity.com/paper/2410.02189/) (2024) - [UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging](https://mlsanity.com/paper/2404.17153/) (2024) - [Test-Driven Development for Code Generation](https://mlsanity.com/paper/2402.13521/) (2024) - [ThinkRepair: Self-Directed Automated Program Repair](https://mlsanity.com/paper/2407.20898/) (2024) - [Creativity in LLM-based Multi-Agent Systems: A Survey](https://mlsanity.com/paper/2505.21116/) (2025) - [Emergent Coordination in Multi-Agent Language Models](https://mlsanity.com/paper/2510.05174/) (2025) - [Analyzing the Performance of Large Language Models on Code Summarization](https://mlsanity.com/paper/2404.08018/) (2024) - [INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair](https://mlsanity.com/paper/2311.09868/) (2023) - [Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios](https://mlsanity.com/paper/2410.12468/) (2024) - [Assemble Foundation Models for Automatic Code Summarization](https://mlsanity.com/paper/2201.05222/) (2022) - [Aligning the Objective of LLM-based Program Repair](https://mlsanity.com/paper/2404.08877/) (2024) - [Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2402.11702/) (2024) - [ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models](https://mlsanity.com/paper/2408.00994/) (2024) - [TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation](https://mlsanity.com/paper/2311.08157/) (2023) - [NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging](https://mlsanity.com/paper/2505.15356/) (2025) ## Built on by (most cited first, 6 of 6) - [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026) - [InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems](https://mlsanity.com/paper/2603.28106/) (2026) - [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026) - [InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading](https://mlsanity.com/paper/2603.13710/) (2026) - [AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair](https://mlsanity.com/paper/2605.04624/) (2026) - [Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies](https://mlsanity.com/paper/2608.05521/) (2026) ## Abstract (arXiv) Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program behavior and hindering precise error localization. In addition, without a way to learn from prior failures, repair processes often fall into repetitive and inefficient cycles. To overcome these challenges, we present TraceCoder, a collaborative multi-agent framework that emulates the observe-analyze-repair process of human experts. The framework first instruments the code with diagnostic probes to capture fine-grained runtime traces, enabling deep insight into its internal execution. It then conducts causal analysis on these traces to accurately identify the root cause of the failure. This process is further enhanced by a novel Historical Lesson Learning Mechanism (HLLM), which distills insights from prior failed repair attempts to inform subsequent correction strategies and prevent recurrence of similar mistakes. To ensure stable convergence, a Rollback Mechanism enforces that each repair iteration constitutes a strict improvement toward the correct solution. Comprehensive experiments across multiple benchmarks show that TraceCoder achieves up to a 34.43% relative improvement in Pass@1 accuracy over existing advanced baselines. Ablation studies verify the significance of each system component, with the iterative repair process alone contributing a 65.61% relative gain in accuracy. Furthermore, TraceCoder significantly outperforms leading iterative methods in terms of both accuracy and cost-efficiency.