arXiv subjects

He Ye

Publications and source records attributed to He Ye.

At least 19 recordsLinked to original sources

arXiv2026

LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation

Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations. We evaluate frontier coding agents paired with widely used loop implementations. The strongest configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks. Recorded plans recover only part of the source-recovered prerequisite DAG, and regression events remain visible across the evaluated loop profiles. We open source the benchmark data and code, including all tasks, more than 5,300 development units, and executable tests, at microsoft/Loopsbench.

cs.SE↗

arXiv2026

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first large-scale empirical study of CLI coding-agent failure trajectories, introducing a process-oriented framework that analyzes failure through its onset, evolution, and recovery across execution trajectories. We first collect 3,843 execution trajectories generated by seven frontier models across three coding-agent scaffolds (OpenHands, MiniSWE, and Terminus2) on Terminal-Bench, then carefully filter them to obtain 1,794 complete and valid trajectories for manual annotation (over 63,000 execution steps), from which we derive 14 findings spanning failure occurrence, root causes, recovery, and cross-system consistency. Our findings show that coding-agent failures are predominantly driven by epistemic errors, typically begin within the first few execution steps, and often remain hidden until recovery is no longer possible, suggesting that improving coding-agent reliability requires earlier validation and intervention rather than relying solely on final-outcome evaluation.

cs.SE↗

arXiv2026

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of 1,530 validated tasks, spanning 18 real-world categories, ranging from short everyday operations to workflows exceeding 50 steps, and covering 1,280 unique commands. From these, we curate a Verified subset of 200 representative, manually reviewed tasks. Comprehensive benchmarking on TerminalWorld-Verified across eight frontier models and six agents reveals that current systems still struggle with authentic terminal workflows, achieving a maximum pass rate of only 62.5%. Moreover, TerminalWorld captures real-world terminal capabilities distinct from existing expert-curated benchmarks (e.g., Terminal-Bench), with only a weak correlation to their scores (Pearson r=0.20). The automated engine makes TerminalWorld authentic and scalable by construction, enabling it to evaluate agents in real-world terminal environments as developer practices evolve. Data and code are available at https://github.com/EuniAI/TerminalWorld.

cs.AI↗

arXiv2026

CodeTracer: Towards Traceable Agent States

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation hard to observe. In these runs, an early misstep can trap the agent in unproductive loops or even cascade into fundamental errors, forming hidden error chains that make it hard to tell when the agent goes off track and why. Existing agent tracing analyses either focus on simple interaction or rely on small-scale manual inspection, which limits their scalability and usefulness for real coding workflows. We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors, reconstructs the full state transition history as a hierarchical trace tree with persistent memory, and performs failure onset localization to pinpoint the failure origin and its downstream chain. To enable systematic evaluation, we construct CodeTraceBench from a large collection of executed trajectories generated by four widely used code agent frameworks on diverse code tasks (e.g., bug fixing, refactoring, and terminal interaction), with supervision at both the stage and step levels for failure localization. Experiments show that CodeTracer substantially outperforms direct prompting and lightweight baselines, and that replaying its diagnostic signals consistently recovers originally failed runs under matched budgets. Our code and data are publicly available.

cs.SE↗

arXiv2026

An Iterative Test-and-Repair Framework for Competitive Code Generation

Large language models (LLMs) have made remarkable progress in code generation, but competitive programming remains a challenge. Recent training-based methods have improved code generation by using reinforcement learning (RL) with execution feedback. The more recent framework CURE further incorporates test generation into the training process, jointly training a Coder and a Tester within a single model. At inference time, the Coder generates many candidate programs, and the Tester generates tests from the problem description. The candidate who passes the most of the generated tests is selected as the final answer. However, CURE has two critical limitations. First, the Tester never reads any candidate code, so its tests often fail to expose implementation-specific bugs. Second, the Coder generates every candidate from scratch and never learns to fix a buggy program based on a failed test. To address these limitations, we propose FixAudit, which approaches competitive code generation from a new perspective: starting from a single initial candidate, it iteratively improves the candidate through a targeted test-and-repair debugging cycle. The framework trains one shared model with two specialized roles through four stages: the Fixer, which repairs the current candidate based on a failing test, and the Auditor, which reads the candidate code to generate new tests that expose its remaining bugs. We evaluate FixAudit on three benchmarks: APPS, CodeContests, and xCodeEval. Applied to a 7B model, the framework surpasses the average performance of the larger 32B baseline within the same model family under the zero-shot setting. Compared to strong baselines built on the same 7B base model, FixAudit improves average Pass@1 by 35.1% to 36.8% and average AvgPassRatio by 7.1% to 24.5%.

cs.SE↗

arXiv2026

ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning

Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, primarily in two forms: (1) input-output (I/O) prediction chains and (2) natural-language descriptions of execution traces. However, intermediate execution steps cannot be explicitly verified during SFT, so the training objective can reduce to merely matching teacher explanations. Moreover, training data is typically collected without explicit control over task difficulty. We introduce ExecVerify, which goes beyond text imitation by incorporating verifiable white-box rewards derived from execution traces, including next-statement prediction and variable value/type prediction. Our work first builds a dataset with multiple difficulty levels via constraint-based program synthesis. Then, we apply reinforcement learning (RL) to reward correct answers about both intermediate execution steps and final outputs, aligning the training objective with semantic correctness at each execution step. Finally, we adopt a two-stage training pipeline that first enhances execution reasoning and then transfers to code generation. Experiments demonstrate that a 7B model trained with ExecVerify achieves performance comparable to 32B models on code reasoning benchmarks and improves pass@1 by up to 5.9\% on code generation tasks over strong post-training baselines.

cs.SE↗

arXiv2026

Echo: Graph-Enhanced Retrieval and Execution Feedback for Issue Reproduction Test Generation

Identifying the root cause of a bug remains difficult for many developers because bug reports often lack a bug reproducing test case that reliably triggers the failure. Manually writing such test cases is time-consuming and requires substantial effort to understand the codebase and isolate the failing behavior. To address this challenge, we propose Echo, an agent for generating issue reproducing test cases, which advances previous work in several ways. During generation, Echo strengthens context retrieval by leveraging a code graph and a novel automatic query-refinement strategy. Echo also improves upon previous tools by automatically executing generated test cases, a first-of-its-kind feature that seamlessly integrates into practical development workflows. In addition, Echo generates potential patches and uses the patched version to validate whether a candidate test meets the fail-to-pass criterion and to provide actionable feedback for refinement. Unlike prior bug-reproduction agents that sample and rank multiple candidate tests, Echo generates a single test per issue, offering a better cost-performance trade-off. Experiments on SWT-Bench Verified show that Echo establishes a new state of the art among open-source approaches, achieving a 66.28% success rate.

cs.SE↗

arXiv2026

JMigBench: A Benchmark for Evaluating LLMs on Source Code Migration (Java 8 to Java 11)

We build a benchmark to evaluate large language models (LLMs) for source code migration tasks, specifically upgrading functions from Java 8 to Java 11. We first collected a dataset of function pairs from open-source repositories, but limitations in data quality led us to construct a refined dataset covering eight categories of deprecated APIs. Using this dataset, the Mistral Codestral model was evaluated with CodeBLEU and keyword-based metrics to measure lexical and semantic similarity as well as migration correctness. Results show that the evaluated model (Mistral Codestral) can handle trivial one-to-one API substitutions with moderate success, achieving identical migrations in 11.11% of the cases, but it struggles with more complex migrations such as CORBA or JAX-WS. These findings suggest Mistral Codestral can partially reduce developer effort by automating repetitive migration tasks but cannot yet replace humans within the scope of the JMigBench benchmark. The benchmark and analysis provide a foundation for future work on expanding datasets, refining prompting strategies, and improving migration performance across different LLMs.

cs.SE↗

arXiv2026

Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents

Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on automated code migration which including refactoring, API adaptation, and dependency updates has advanced rapidly, the exploration of the automated environment interaction that must accompany it remains relatively scarce. In practice, code and its environment are intricately intertwined. Relying solely on static analysis of the environment leads to an inadequate understanding of the target setting, prolongs feedback cycles, and consequently causes significant rework and project delays, thereby reducing overall efficiency. We contend that successful software evolution demands a holistic perspective that integrates both code and environment migration. To understand the current landscape and challenges, we first provide an overview of the status of automated environment construction. We then propose a novel framework paradigm that tightly integrates automated environment setup with the code migration workflow. Finally, we explore the challenges and future directions for automated environment interaction within the code migration domain. Our findings emphasize that without automated environment interaction, the automation of code migration is only half complete.

cs.SE↗

arXiv2026

HerAgent: Rethinking the Automated Environment Deployment via Hierarchical Test Pyramid

Automated software environment setup is a prerequisite for testing, debugging, and reproducing failures, yet remains challenging in practice due to complex dependencies, heterogeneous build systems, and incomplete documentation. Recent work leverages large language models to automate this process, but typically evaluates success using weak signals such as dependency installation or partial test execution, which do not ensure that a project can actually run. In this paper, we argue that environment setup success should be evaluated through executable evidence rather than a single binary signal. We introduce the Environment Maturity Hierarchy, which defines three success levels based on progressively stronger execution requirements, culminating in successful execution of a project's main entry point. Guided by this hierarchy, we propose HerAgent, an automated environment setup approach that incrementally constructs executable environments through execution-based validation and repair. We evaluate HerAgent on four public benchmarks, where it outperforms all related work, achieving up to 79.6\% improvement due to its holistic understanding of project structure and dependencies. On complex C/C++ projects, HerAgent surpasses prior approaches by 66.7\%. In addition, HerAgent uniquely resolves 11-30 environment instances across the benchmarks that no prior method can configure.

cs.SE↗

arXiv2026

ContextBench: A Benchmark for Context Retrieval in Coding Agents

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks.

cs.LG↗

arXiv2025

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive capabilities in automated issue resolution, their decision-making processes remain largely opaque. This paper presents an empirical study of agent trajectories, namely the execution traces capturing the steps agents take when attempting to resolve software issues. We analyse trajectories from three state-of-the-art code agents (OpenHands, SWE-agent, and Prometheus) on the SWE-Bench benchmark, examining both successful and failed attempts. Our investigation reveals several key insights into agent behaviour. First, we identify how distinct problem-solving strategies, such as defensive programming and context gathering, enable success in different scenarios. Second, we find that failed trajectories are consistently longer and exhibit higher variance than successful ones, with failure patterns differing significantly between agents. Third, our fault localisation analysis shows that while most trajectories correctly identify problematic files (72-81\% even in failures), success depends more on achieving approximate rather than exact code modifications. These and other findings unveiled by our study, provide a foundation for understanding agent behaviour through trajectory analysis, contributing to the development of more robust and interpretable autonomous software engineering systems.

cs.SE↗

arXiv2025

Generative AI for Testing of Autonomous Driving Systems: A Survey

Autonomous driving systems (ADS) have been an active area of research, with the potential to deliver significant benefits to society. However, before large-scale deployment on public roads, extensive testing is necessary to validate their functionality and safety under diverse driving conditions. Therefore, different testing approaches are required, and achieving effective and efficient testing of ADS remains an open challenge. Recently, generative AI has emerged as a powerful tool across many domains, and it is increasingly being applied to ADS testing due to its ability to interpret context, reason about complex tasks, and generate diverse outputs. To gain a deeper understanding of its role in ADS testing, we systematically analyzed 91 relevant studies and synthesized their findings into six major application categories, primarily centered on scenario-based testing of ADS. We also reviewed their effectiveness and compiled a wide range of datasets, simulators, ADS, metrics, and benchmarks used for evaluation, while identifying 27 limitations. This survey provides an overview and practical insights into the use of generative AI for testing ADS, highlights existing challenges, and outlines directions for future research in this rapidly evolving field.

cs.SE↗

arXiv2025

Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving

Large Language Models (LLMs) have shown remarkable capabilities in automating software engineering tasks, spurring the emergence of coding agents that scaffold LLMs with external tools to resolve repository-level problems. However, existing agents still struggle to navigate large-scale codebases, as the Needle-in-a-Haystack problem persists even with million-token context windows, where relevant evidence is often overwhelmed by large volumes of irrelevant code and documentation. Prior codebase navigation approaches, including embedding-based retrieval, file-system exploration, and graph-based retrieval, address parts of this challenge but fail to capture the temporal continuity of agent reasoning, rendering agents stateless and causing repeated repository traversals that hinder scalable planning and reasoning. To address these limitations, we present Prometheus, a memory-centric coding agent framework for long-horizon codebase navigation. Prometheus represents the repository as a unified knowledge graph to encode semantic dependencies and employs a context engine augmented with working memory that retains and reuses previously explored contexts to ensure continuity across reasoning steps. Built upon this engine, Prometheus integrates memory-enhanced navigation into a multi-agent system for automated issue resolution, encompassing issue classification, bug reproduction, patch generation, and verification. Comprehensive experiments are conducted on two widely used issue resolution benchmarks, i.e., SWE-bench Verified and SWE-PolyBench Verified. Powered by GPT-5, Prometheus achieves state-of-the-art performance with 74.4% and 33.8% resolution rates on the two benchmarks, ranking Top-6 and Top-1 among open-source agent systems, respectively. Our data and code are available at https://github.com/EuniAI/Prometheus.

cs.SE↗

arXiv2025

CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific statement will be executed. This capability is essential for downstream tasks like debugging, code generation, and program repair. Prior approaches mainly rely on supervised fine-tuning to improve performance in code reasoning tasks. However, they often show limited gains and fail to generalize across diverse scenarios. We argue this is due to two core issues: the low quality of training data and the limitations of supervised fine-tuning, which struggles to teach general reasoning skills. To address these challenges, we propose CodeReasoner, a framework that spans both dataset construction and a two-stage training process. First, we introduce a method to construct datasets that focus on the core execution logic of Python programs. Next, we apply instruction tuning to inject execution-specific knowledge distilled from a powerful teacher model. We then enhance reasoning and generalization through GRPO reinforcement learning on top of the fine-tuned model. Experiments on three widely-used code reasoning benchmarks show that CodeReasoner improves performance by 27.1% to 40.2% over prior methods using a 7B model. Notably, the 7B model matches GPT-4o on key tasks like input/output and coverage prediction. When scaled to 14B, CodeReasoner outperforms GPT-4o across all benchmarks. Ablation studies confirm the effectiveness of each training stage and highlight the importance of reasoning chains.

cs.SE↗

arXiv2025

What Exactly Does Guidance Do in Masked Discrete Diffusion Models

We study masked discrete diffusion models with classifier-free guidance (CFG). Assuming no score error nor discretization error, we derive an explicit solution to the guided reverse dynamics, so that how guidance influences the sampling behavior can be precisely characterized. When the full data distribution is a mixture over classes and the goal is to sample from a specific class, guidance amplifies class-specific regions while suppresses regions shared with other classes. This effect depends on the guidance strength $w$ and induces distinct covariance structures in the sampled distribution. Notably, we observe quantitatively different behaviors in $1$D and $2$D. We also show that for large $w$, the decay rate of the total variation ($\mathrm{TV}$) along the reverse dynamics is double-exponential in $w$ for both $1$D and $2$D. These findings highlight the role of guidance, not just in shaping the output distribution, but also in controlling the dynamics of the sampling trajectory. Our theoretical analysis is supported by experiments that illustrate the geometric effects of guidance and its impact on convergence.

stat.ML↗

arXiv2025

Adversarial Reasoning for Repair Based on Inferred Program Intent

Automated program repair (APR) has shown promising results, particularly with the use of neural networks. Currently, most APR tools focus on code transformations specified by test suites, rather than reasoning about the program intent and the high-level bug specification. Without a proper understanding of program intent, these tools tend to generate patches that overfit incomplete test suites and fail to reflect the developers intentions. However, reasoning about program intent is challenging. In our work, we propose an approach called AdverIntent-Agent, based on critique and adversarial reasoning. Our approach is novel to shift the focus from generating multiple APR patches to inferring multiple potential program intents. Ideally, we aim to infer intents that are, to some extent, adversarial to each other, maximizing the probability that at least one aligns closely with the developers original intent. AdverIntent-Agent is a multi-agent approach consisting of three agents: a reasoning agent, a test agent, and a repair agent. First, the reasoning agent generates adversarial program intents along with the corresponding faulty statements. Next, the test agent produces adversarial test cases that align with each inferred intent, constructing oracles that use the same inputs but have different expected outputs. Finally, the repair agent uses dynamic and precise LLM prompts to generate patches that satisfy both the inferred program intent and the generated tests. AdverIntent-Agent was evaluated on two benchmarks: Defects4J 2.0 and HumanEval-Java. AdverIntent-Agent correctly repaired 77 and 105 bugs in both benchmarks, respectively.

cs.SE↗

arXiv2025

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation

The growing use of large language models (LLMs) has increased the importance of natural language (NL) in software engineering. However, ambiguity of NL can harm software quality, as unclear problem descriptions may lead to incorrect program generation. Detecting and resolving such ambiguity is challenging, motivating our introduction of the automated repair of ambiguous NL descriptions, which we approach by reducing code generation uncertainty and better aligning NL with input-output examples. Ambiguity repair is difficult for LLMs because they must understand how their interpretation of a description changes when the text is altered. We find that directly prompting LLMs to clarify ambiguity often produces irrelevant or inconsistent edits. To address this, we decompose this task into two simpler steps: (1) analyzing and repairing the LLM's interpretation of the description - captured by the distribution of programs it induces - using traditional testing and program repair, and (2) refining the description based on distribution changes via a method we call contrastive specification inference. We implement this approach in a tool called SpecFix and evaluate it using four state-of-the-art LLMs (GPT-4o, GPT-4o-mini, DeepSeek-V3, and Qwen2.5-Coder-32B-Instruct) on three popular code generation benchmarks (HumanEval+, MBPP+ and LiveCodeBench). Without human intervention or external information, SpecFix modified 43.58% of descriptions, improving Pass@1 on the modified set by 30.9%. This yields a 4.09% absolute improvement across the entire benchmark. Repairs also transfer across models: descriptions repaired for one model improve other models' performance by 10.48%.

cs.SE↗