Build-bench is the first architecture-aware benchmark that evaluates LLMs on repairing cross-ISA build failures via iterative tool-augmented reasoning, with the best model reaching 63.19% success.
hub
Bissyandé, Yang Liu, and Haoye Tian
15 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
15
Pith papers citing it
1
external citations · external index
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
PatchFusion uses deterministic atomic evidence fusion on candidate patches to outperform ranking, test-filtering, and LLM-judge selectors on SWE-bench and Defects4J pools.
Introduces InterFLOPBench benchmark and evaluates 14 LLMs on multi-label classification of six floating-point error categories in C code, with top models exceeding 0.88 overall F1 but lower scores on subtle errors like underflow.
A11YRepair uses divide-and-conquer clustering and WCAG knowledge to repair multi-fault accessibility violations in web projects, showing better results than baselines on a new 60-project benchmark with some patches merged upstream.
RECENT decouples skill semantics from embodiment-specific bindings via code refactoring to let small language models achieve skill grounding performance matching large language model baselines.
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
Continuous latent-vector compression improves BLEU scores on repository-level code tasks by up to 28.3% at 4x compression while cutting inference latency.
A framework combining universal AST normalization, hybrid graph-LLM embeddings, and strict execution-grounded validation achieves 89-92% intra-language accuracy and 74-80% cross-language F1 while resolving 70% of vulnerabilities at 12% failure rate.
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
Frontier LLMs like GPT-5.2 show large accuracy drops on perturbed program-output prediction tasks while open-source reasoning models remain more stable, exposing limits in code semantics understanding.
MOA deploys LLM agents to detect recurring memory anti-patterns via profiling, synthesize static analyzers, and apply patches, reporting 42% heap and 11% binary-size reductions on OpenHarmony after finding over 10,000 issues.
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
HELO-APR uses cross-lingual synthetic data generation and curriculum learning to improve LLM-based automatic program repair in low-resource programming languages.
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprepared for deployable fair systems.
citing papers explorer
-
Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
Build-bench is the first architecture-aware benchmark that evaluates LLMs on repairing cross-ISA build failures via iterative tool-augmented reasoning, with the best model reaching 63.19% success.
-
A Single Patch Is Not Enough: Deterministic Fusion of Repair Candidates
PatchFusion uses deterministic atomic evidence fusion on candidate patches to outperform ranking, test-filtering, and LLM-judge selectors on SWE-bench and Defects4J pools.
-
Benchmarking Large Language Models on Floating-Point Error Classification
Introduces InterFLOPBench benchmark and evaluates 14 LLMs on multi-label classification of six floating-point error categories in C code, with top models exceeding 0.88 overall F1 but lower scores on subtle errors like underflow.
-
A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair
A11YRepair uses divide-and-conquer clustering and WCAG knowledge to repair multi-fault accessibility violations in web projects, showing better results than baselines on a new 60-project benchmark with some patches merged upstream.
-
Efficient Skill Grounding via Code Refactoring with Small Language Models
RECENT decouples skill semantics from embodiment-specific bindings via code refactoring to let small language models achieve skill grounding performance matching large language model baselines.
-
BLAgent: Agentic RAG for File-Level Bug Localization
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
-
On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation
Continuous latent-vector compression improves BLEU scores on repository-level code tasks by up to 28.3% at 4x compression while cutting inference latency.
-
Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
A framework combining universal AST normalization, hybrid graph-LLM embeddings, and strict execution-grounded validation achieves 89-92% intra-language accuracy and 74-80% cross-language F1 while resolving 70% of vulnerabilities at 12% failure rate.
-
PAFT: Preservation Aware Fine-Tuning for Minimal-Edit Program Repair
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
-
How Robustly do LLMs Understand Execution Semantics?
Frontier LLMs like GPT-5.2 show large accuracy drops on perturbed program-output prediction tasks while open-source reasoning models remain more stable, exposing limits in code semantics understanding.
-
MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale
MOA deploys LLM agents to detect recurring memory anti-patterns via profiling, synthesize static analyzers, and apply patches, reporting 42% heap and 11% binary-size reductions on OpenHarmony after finding over 10,000 issues.
-
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
-
HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer
HELO-APR uses cross-lingual synthetic data generation and curriculum learning to improve LLM-based automatic program repair in low-resource programming languages.
-
Sustainable Code Generation Using Large Language Models: A Systematic Literature Review
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
-
Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprepared for deployable fair systems.