arXiv subjects

Minh Le-Anh

Publications and source records attributed to Minh Le-Anh.

9 recordsLinked to original sources

arXiv2026

Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation

Repository-level code generation requires generated code to be compatible not only with the target repository but also with its dependency environment. Existing retrieval-based methods mainly retrieve context from the local repository, leaving external API usage dependent on the model's pretrained knowledge, which can be insufficient for unseen or version-specific APIs. Moreover, current retrieval strategies largely focus on one-hop evidence and overlook the structural relationships among code components. We propose CrossCoder, a cross-repository code generation framework that explicitly incorporates external libraries into the retrieval context through a unified knowledge graph over repository and library entities. CrossCoder identifies important nodes via planning and semantic retrieval, then selectively expands neighboring nodes to retrieve richer multi-hop contextual evidence for generation. To further evaluate dependency-version compatibility, we introduce VersionExec, an execution-based benchmark derived from BigCodeBench that evaluates generation under different dependency versions. Experimental results on RepoExec, DevEval, and VersionExec demonstrate that CrossCoder consistently improves both functional correctness (up to 6.3% on pass@1) and robustness to dependency-version changes.

cs.SE↗

arXiv2026

Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond

Large language models for code (CodeLLMs) have demonstrated remarkable success in standalone code completion and generation, sometimes even surpassing human performance, yet their effectiveness diminishes in repository-level settings where cross-file dependencies and structural context are essential. Existing Retrieval-Augmented Generation (RAG) approaches often borrow strategies from NLP, relying on chunking-based indexing and similarity-based retrieval. Chunking results in the loss of coherence between code units and overlooks structural relationships, while similarity-driven methods frequently miss functionally relevant dependencies such as helper functions, classes, or global variables. To address these limitations, we present Hydra, a repository-level code generation framework that treats code as structured code rather than natural language. Our approach introduces (i) a structure-aware indexing strategy that represents repositories as hierarchical trees of functions, classes, and variables, preserving code structure and dependencies, (ii) a lightweight dependency-aware retriever (DAR) that explicitly identifies and retrieves the true dependencies required by a target function, and (iii) a hybrid retrieval mechanism that combines DAR with similarity-based retrieval to provide both essential building blocks and practical usage examples. Extensive experiments on the challenging DevEval and RepoExec benchmarks, both requiring function implementation from real-world repositories with complex large repository context, show that Hydra achieves state-of-the-art performance across open- and closed-source CodeLLMs. Notably, our method establishes a new state of the art in repository-level code generation, surpassing strongest baseline by over 5% in Pass@1 and even enabling smaller models to match or exceed the performance of much larger ones that rely on existing retrievers.

cs.SE↗

arXiv2026

Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals

Automated Program Repair (APR) has recently benefited from large language models (LLMs). However, most LLM-based APR approaches still rely primarily on coarse-grained, end-to-end signals from test-suite outcomes or specification checks on the candidate fix to guide repair, providing limited insight into where a program's internal logic deviates from its intended behavior. In contrast, human debugging often relies on intermediate reasoning about program states through localized correctness conditions or assertions. Inspired by this observation, we propose SpecTune, a specification-guided debugging framework that incorporates intermediate behavioral reasoning into APR. SpecTune decomposes the repair task into suspicious regions connected by execution checkpoints and derives localized postconditions representing expected program behaviors at those points. By executing the buggy program and evaluating these postconditions, SpecTune produces micro-level debugging signals that indicate mismatches between observed and intended behaviors, enabling more precise fault localization and targeted patch generation. To address the potential unreliability of LLM-generated postconditions, we introduce two complementary signals: a specification validation signal alpha, which estimates the consistency of generated postconditions using partial passing test cases, and a discriminative signal beta, which detects violations of validated postconditions during execution. With these signals, SpecTune safely leverages automatically generated specifications for APR. Experimental results show that SpecTune improves fault localization and APR effectiveness than the baselines.

cs.SE↗

arXiv2026

Teaching Code LLMs to Reason with Intermediate Formal Specifications

Unlike natural-language specifications, executable formal specifications provide machine-checkable constraints for verifying, debugging, and repairing code. However, writing such specifications is labor-intensive, and existing LLM-based methods mainly infer whole-program pre/postconditions, missing the intermediate semantic commitments that programmers rely on when reasoning about an algorithm. Our study further shows that prompting current CodeLLMs often produces executable assertions that are syntactically invalid, trivial, or too weak to reject behavior-changing faults. In this paper, we study executable checkpoint specification generation, where assertions are inserted at meaningful internal program points to describe expected intermediate states. We introduce SpecCoder, a verification-guided CodeLLM training framework that learns from validated reference programs, behavior-changing mutants, and multi-turn specification-refinement traces. SpecCoder selects specifications that hold on correct executions while rejecting faulty executions, turning specifications from passive annotations into executable evidence. To evaluate this setting, we introduce HumanExec, a benchmark built from recent Codeforces competitive programming problems with test suites, reference solutions, and human buggy submissions, supporting three tasks: specification generation, program correctness checking, and program repair. Experiments on HumanExec show that SpecCoder substantially improves checkpoint-specification quality over base CodeLLMs. Across Qwen2.5-Coder models, SpecCoder improves inline-specification correctness by up to 55.8%, completeness by up to 358.1%, and executable assertion validity by up to 26.6%. These gains further translate to downstream correctness reasoning and repair, showing that executable checkpoints provide fine-grained evidence for reliable verification.

cs.SE↗

arXiv2026

Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback

Large language models (LLMs) are typically evaluated on code generation and program repair using binary functional correctness: a generated program or patch either passes or fails a test suite. This protocol is simple but coarse, as it ignores partial progress, feedback use, regressions, and the refinement trajectory through which models often improve code. We introduce PAIR-Bench, a progressive and adaptive benchmark for evaluating code improvement: transforming an incorrect or incomplete program into a more correct one through feedback-guided refinement. PAIR-Bench uses progressive hinting, a structured feedback protocol with two controls. Failure-region control determines what the feedback targets by grouping hidden failing tests into failure scenarios, while hint-depth control determines how much repair-relevant information is revealed, from coarse symptoms to implementation-level guidance. This design enables PAIR-Bench to measure whether a model repairs targeted failures, generalizes beyond the hint, preserves already-correct behavior, and how much assistance it requires. By evaluating repair trajectories progressive metrics rather than only final pass/fail outcomes, PAIR-Bench provides a finer-grained assessment of LLM code-improvement capability.

cs.SE↗

arXiv2026

Documentation-Guided Agentic Codebase Migration from C to Rust

Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss architectural intent. We present RustPrint, a documentation-guided agentic framework for repository-level C-to-Rust migration. RustPrint first converts the source repository into architecture-aware documentation and treats it as a migration blueprint capturing module structure, data flow, APIs, and design rationale. Coding agents then use this blueprint to plan crates, implement modules, check compilability, reduce unsafe code, and iteratively refine the translated repository. RustPrint next compares documentation from the Rust output against the source documentation and uses mismatches as repair signals. It also translates and runs source test suites so runtime failures can guide targeted fixes. Experiments on eight real-world C repositories ranging from 11K to 84K LoC show that RustPrint compiles every target under both an open-weight (Kimi-K2-Instruct) and a closed-weight (GPT-5.4) backbone, while prior LLM-based translators (Self-Repair, EvoC2Rust) fail repository-wide. With the open-weight Kimi-K2-Instruct backbone, RustPrint exceeds an agentic Claude Code baseline on feature preservation (93.26% vs. 52.52%) and on cross-evaluation test pass rate (95.17% vs. 79.85%). These results suggest that documentation-guided coordination is a useful direction for scalable codebase migration.

cs.SE↗

arXiv2026

CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases

Given a large and evolving codebase, the ability to automatically generate holistic, architecture-aware documentation that captures not only individual functions but also cross-file, cross-module, and system-level interactions remains an open challenge. Comprehensive documentation is essential for long-term software maintenance and collaboration, yet current automated approaches still fail to model the rich semantic dependencies and architectural structures that define real-world software systems. We present \textbf{CodeWiki}, a unified framework for automated repository-level documentation across seven programming languages. CodeWiki introduces three key innovations: (i) hierarchical decomposition that preserves architectural context across multiple levels of granularity, (ii) recursive multi-agent processing with dynamic task delegation for scalable generation, and (iii) multi-modal synthesis that integrates textual descriptions with visual artifacts such as architecture diagrams and data-flow representations. To enable rigorous evaluation, we introduce \textbf{CodeWikiBench}, a comprehensive benchmark featuring multi-dimensional rubrics and LLM-based assessment protocols. Experimental results show that CodeWiki achieves a 68.79\% quality score with proprietary models, outperforming the closed-source DeepWiki baseline (64.06\%) by 4.73\%, with particularly strong improvements on high-level scripting languages (+10.47\%). We open-source CodeWiki to foster future research and community adoption.

cs.SE↗

arXiv2026

Semantic Evolution over Populations for LLM-Guided Automated Program Repair

Large language models (LLMs) have recently shown strong potential for automated program repair (APR), particularly through iterative refinement that generates and improves candidate patches. However, state-of-the-art iterative refinement LLM-based APR approaches cannot fully address challenges, including maintaining useful diversity among repair hypotheses, identifying semantically related repair families, composing complementary partial fixes, exploiting structured failure information, and escaping structurally flawed search regions. In this paper, we propose a Population-Based Semantic Evolution framework for APR iterative refinement, called EvolRepair, that formulates LLM-based APR as a semantic evolutionary algorithm. EvolRepair reformulates the search paradigm of classic genetic algorithm for APR, but replaces its syntax-based operators with semantics-aware components powered by LLMs and structured execution feedback. Candidate repairs are organized into behaviorally coherent groups, enabling the algorithm to preserve diversity, reason over repair families, and synthesize stronger candidates by recombining complementary repair insights across the population. By leveraging structured failure patterns to guide search direction, EvolRepair can both refine promising repair strategies and shift toward alternative abstractions when necessary. Our experiments show that EvolRepair substantially improves repair effectiveness over existing LLM-based APR approaches.

cs.SE↗

arXiv2026

FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning

The growing collaboration between humans and AI models in generative tasks has introduced new challenges in distinguishing between human-written, LLM-generated, and human-LLM collaborative texts. In this work, we collect a multilingual, multi-domain, multi-generator dataset FAIDSet. We further introduce a fine-grained detection framework FAID to classify text into these three categories, and also to identify the underlying LLM family of the generator. Unlike existing binary classifiers, FAID is built to capture both authorship and model-specific characteristics. Our method combines multi-level contrastive learning with multi-task auxiliary classification to learn subtle stylistic cues. By modeling LLM families as distinct stylistic entities, we incorporate an adaptation to address distributional shifts without retraining for unseen data. Our experimental results demonstrate that FAID outperforms several baselines, particularly enhancing the generalization accuracy on unseen domains and new LLMs, thus offering a potential solution for improving transparency and accountability in AI-assisted writing. Our data and code are available at https://github.com/mbzuai-nlp/FAID

cs.CL↗