analiza aiqbench
HAFixAgent demonstrates that integrating repository history into agentic automated program repair significantly boosts success rates, particularly for weaker base models, without incurring prohibitive token costs. This research advances the practical capabilities of Large Language Models in software engineering by showing how context injection can solve a broader range of bugs than state-of-the-art non-history agents.
HAFixAgent: History-Aware Agentic Program Repair
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that repository history can help repair single-line bugs. We conduct a large-scale empirical study of whether, how much, and under what conditions repository history improves agentic APR beyond this setting. We present HAFixAgent, a history-aware program repair agent that injects blame-derived repository context into its repair loop. Across 854 Defects4J (Java) and 501 BugsInPy (Python) bugs, we first show that bug-relevant history is widely available. We then evaluate HAFixAgent across three base models under perfect fault localization. The best history heuristic improves over non-history from +4.4% on Defects4J and +1.1% on BugsInPy with the strongest model to as much as +64.3% with weaker models. HAFixAgent also outperforms RepairAgent by +56.6% and BIRCH-feedback by +47.1% on the strongest model, showing that it is a strong repair agent independent of history. The three history heuristics are complementary: each repairs a different subset of bugs, so their hybrid significantly repairs more bugs than non-history (McNemar's test, p < 0.001), and this advantage persists under realistic spectrum-based fault localization. Individual history heuristics are generally no more expensive than non-history in agent steps or tokens under either localization setting, while the hybrid costs roughly twice a single run in a cascade setting.
Abstract:Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that repository history can help repair single-line bugs. We conduct a large-scale empirical study of whether, how much, and under what conditions repository history improves agentic APR beyond this setting. We present HAFixAgent, a history-aware program repair agent that injects blame-derived repository context into its repair loop. Across 854 Defects4J (Java) and 501 BugsInPy (Python) bugs, we first show that bug-relevant history is widely available. We then evaluate HAFixAgent across three base models under perfect fault localization. The best history heuristic improves over non-history from +4.4% on Defects4J and +1.1% on BugsInPy with the strongest model to as much as +64.3% with weaker models. HAFixAgent also outperforms RepairAgent by +56.6% and BIRCH-feedback by +47.1% on the strongest model, showing that it is a strong repair agent independent of history. The three history heuristics are complementary: each repairs a different subset of bugs, so their hybrid significantly repairs more bugs than non-history (McNemar's test, p < 0.001), and this advantage persists under realistic spectrum-based fault localization. Individual history heuristics are generally no more expensive than non-history in agent steps or tokens under either localization setting, while the hybrid costs roughly twice a single run in a cascade setting.
Evaluation: on both realistic spectrum-based fault localization and perfect fault localization Benchmarks: Defects4J and BugsInPy Subject LLMs: DeepSeek-V3.2-Exp, Qwen3-Coder-Next, and Devstral-Small-2
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
arXiv:2511.01047 [cs.SE]
(or arXiv:2511.01047v4 [cs.SE] for this version)
Text integral sub licența deschisă a publicației · 250 cuvinte
Subiecte conexe
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
arXiv · 11 iun. 2026
MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation
arXiv · 11 iun. 2026
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
Hugging Face · 1 iun. 2026