arXiv subjects

Pengfei Gao

Publications and source records attributed to Pengfei Gao.

At least 19 recordsLinked to original sources

arXiv2026

Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?

Modern software systems rely heavily on third-party dependencies, but upgrading those dependencies remains a costly maintenance activity. Dependency upgrades do not always preserve the function signatures, type systems, APIs, or runtime semantics assumed by existing code. Consequently, developers often need to perform source code adaptations to accommodate dependency-induced changes. However, such code-level changes are often not explicitly communicated to project maintainers, posing a significant challenge to software reliability. Meanwhile, coding agents have emerged as a new form of software development tool and are increasingly adopted by developers due to their automation capabilities. In this paper, we introduce DEPBENCH, a benchmark consisting of 203 real-world dependency-upgrade tasks across five package ecosystems spanning five language communities, each involving hidden code-level changes that require source code adaptation. We evaluate mainstream coding agents on DEPBENCH. The best completed configuration solves only 104/203 tasks (51.2%), with substantial variation across agent harnesses, models, and ecosystems, highlighting an important gap between current agent capabilities and real-world software maintenance needs.

cs.SE↗

arXiv2026

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses can substantially improve robustness, harness design remains a manual and expensive process that requires searching over a large space of prompts, tool configurations, and control logic. We propose AutoSaddler, an automatic harness optimization framework that formulates harness improvement as an offline learning problem and iteratively updates the harness using failure signals from mini-batches. AutoSaddler combines failure-trace diagnosis, structured patch generation that treats the harness as code, and validation-based update selection. Experiments on GAIA2, SWE-Bench Pro, and Terminal-Bench 2.0 show that AutoSaddler substantially improves agent performance over the corresponding base harnesses, achieving gains of 9.0, 9.6, and 10.0 percentage points, respectively. Ablation studies further suggest that effective harness optimization benefits from three ingredients: deep debugging rather than shallow reflection, targeted modifications rather than unconstrained editing, and generalization-aware selection rather than trajectory-specific repair. Together, these results suggest that automatic harness optimization is a promising path toward more performant and reliable agent systems.

cs.AI↗

arXiv2026

DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation

Reproduction test generation, producing a failing-then-passing test that captures a reported bug, is a critical step in automated software engineering. Existing agentic methods treat this as a monolithic loop, despite the task inherently comprising two subtasks of distinct nature: diagnosing the root cause and writing a fail-to-pass test. Without explicit separation, the agent faces a compound objective with underspecified intermediate goals, leading to goal drift. We propose DPIAgent, a structured agentic framework built on three principles, Divide, Protocol, Isolate (DPI), that mitigates compound-objective ambiguity and goal drift: it Divides the task into single-objective phases of defect exploration and test generation; enforces a handoff Protocol that records the diagnosis and test plan, preventing context loss; and Isolates each phase's action space by tailoring the toolset to its task, preventing irrelevant tools from misleading execution. On SWT-Bench Verified, DPIAgent outperforms seven baselines across three backbone LLMs. With DPI alone it reaches 81.76% success rate on GPT-5, the highest reported among open-source methods, gaining up to 11.88 points over the strongest baseline on GPT-5-Mini; adding test selection further raises it to 86.17%. Our analysis shows that architectural structure and backbone capability are complementary axes rather than substitutes, demonstrating DPI's generalizability across model classes.

cs.SE↗

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

EntropyMoE: Entropy-Aware Sparse Expert Routing for Tokenizer-Free LLMs

Recent byte-level large language models (LLMs) have made tokenizer-free modeling increasingly competitive by grouping bytes into dynamically sized patches. However, existing byte-patch architectures still apply the same dense feed-forward computation to every patch. This uniform computation cannot adapt model capacity to variations in patch semantics and granularity. We address this limitation with EntropyMoE, a Mixture-of-Experts (MoE) architecture designed for dynamic byte patches. EntropyMoE replaces the dense feed-forward modules in the global patch Transformer with Top-K expert layers. Each dynamic patch serves as the basic unit of expert routing, and its byte coverage determines its contribution to workload accounting. The router selects experts directly from patch entropy, using the same granularity signal that underlies dynamic patch construction to organize sparse computation. Patch entropy and length jointly define the feature space for regulating expert specialization. Experiments show that EntropyMoE achieves the lowest held-out bits-per-byte among matched dense and sparse baselines while maintaining comparable downstream accuracy. These results establish patch entropy as an effective routing coordinate for sparse conditional computation and extend Mixture-of-Experts modeling beyond tokenizer-based representations.

cs.AI↗

arXiv2026

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests into verified tasks on healthy modern revisions of the same repository. It aligns historical evidence with evolved code, reconstructs task states through Patch Reversal, Code Mapping, or Agent Reconstruction, and validates the lifecycle from a healthy base to a task state and a restored state. By deriving multiple tasks grounded in developer evidence from maintained environments, Change2Task provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task construction effort. We evaluate the system through five common and widely adopted coding agent task families: Bug Fix, Feature Addition, Test Generation, Application Programming Interface Migration, and Security Repair. Starting from 1,130 source changes eligible for construction, Change2Task achieves 79.6% verified task construction success across these task families. On a matched candidate set, it recovers 29.2% more verified tasks than a construction baseline based on pull requests. Historical and reconstructed cases achieve up to 98.0% matched outcome agreement under agent evaluation, while reuse of modern bases reduces measured expenditure across the complete pipeline by 10.8%.

cs.SE↗

arXiv2026

Can Large Language Models Generate Observability-Aware Code?

Recent advances in coding agents have enabled the generation of increasingly complex software systems. While existing evaluations primarily focus on functional correctness, production systems must expose failure evidence to support observability. In this paper, we present a systematic study of observability in agent-generated systems. We examine whether agents can reconstruct source-level diagnostic semantics by restoring observability artifacts in 10 open-source and 8 industrial repositories. We also evaluate whether these artifacts translate into effective fault signals at runtime through 200 generated microservice systems deployed on Kubernetes with 13 injected faults. Our results reveal a consistent gap between diagnostic semantics at the source level and fault signals (i.e., explicit, fault-specific evidence) at runtime. At the source level, agents partially recover observability artifacts but struggle to capture key diagnostic semantics. At runtime, generated systems expose fault signals for only a small fraction of failures (up to 13.99\%), despite the presence of logging, suggesting that the generated observability artifacts may lack the failure-specific semantics needed to effectively expose faults. We further introduce an observability-oriented skill, which can serve as a guidance to improve both diagnostic semantics and fault-signal exposure, but the gains remain limited, indicating that the gap is not easily addressed. More broadly, our findings suggest that current evaluations focusing primarily on functional correctness may overlook observability as an important dimension of practical software quality.

cs.SE↗

arXiv2026

Evaluating Repository-level Software Documentation via Question Answering and Feature-Driven Development

Software documentation is crucial for repository comprehension. While Large Language Models (LLMs) advance documentation generation from code snippets to entire repositories, existing benchmarks have two key limitations: (1) they lack a holistic, repository-level assessment, and (2) they rely on unreliable evaluation strategies, such as LLM-as-a-judge, which suffers from vague criteria and limited repository-level knowledge. To address these issues, we introduce SWD-Bench, a novel benchmark for evaluating repository-level software documentation. Inspired by documentation-driven development, our strategy evaluates documentation quality by assessing an LLM's ability to understand and implement functionalities using the documentation, rather than by directly scoring it. This is measured through function-driven Question Answering (QA) tasks. SWD-Bench comprises three interconnected QA tasks: (1) Functionality Detection, to determine if a functionality is described; (2) Functionality Localization, to evaluate the accuracy of locating related files; and (3) Functionality Completion, to measure the comprehensiveness of implementation details. We construct the benchmark, containing 4,170 entries, by mining high-quality Pull Requests and enriching them with repository-level context. Experiments reveal limitations in current documentation generation methods and show that source code provides complementary value. Notably, documentation from the best-performing method improves the issue-solving rate of SWE-Agent by 20.00%, which demonstrates the practical value of high-quality documentation in supporting documentation-driven development.

cs.SE↗

arXiv2026

UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding tasks, failing to achieve a comprehensive and multi-grained video perception. To bridge this gap, we introduce UFVideo, the first Video LLM with unified multi-grained cooperative understanding capabilities. Specifically, we design unified visual-language guided alignment to flexibly handle video understanding across global, pixel and temporal scales within a single model. UFVideo dynamically encodes the visual and text inputs of different tasks and generates the textual response, temporal localization, or grounded mask. Additionally, to evaluate challenging multi-grained video understanding tasks, we construct the UFVideo-Bench consisting of three distinct collaborative tasks within the scales, which demonstrates UFVideo's flexibility and advantages over GPT-4o. Furthermore, we validate the effectiveness of our model across 9 public benchmarks covering various common video understanding tasks, providing valuable insights for future Video LLMs.

cs.CV↗

arXiv2026

Reducing Cost of LLM Agents with Trajectory Reduction

Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness, the high computational cost of input tokens due to ever-growing trajectories remains a significant efficiency concern. Efficiency has been largely overlooked in existing studies and agent products, and this paper addresses this gap by introducing an inference-time trajectory reduction approach that reduces computational costs. By analyzing existing agent trajectories, we demonstrate that useless, redundant, and expired information is widespread across trajectories. Such waste can be identified and reduced without compromising the agent's performance. We propose a simple yet effective trajectory reduction approach, AgentDiet, which automatically removes such waste during agent execution. We implement AgentDiet on a top-performing coding agent, and our evaluation on two LLMs and two benchmarks shows that AgentDiet can reduce input tokens by 39.9%-59.7% and the total computational cost by 21.1%-35.9%, while maintaining the same agent performance. These results indicate that inference-time trajectory reduction is a promising direction for agent systems.

cs.SE↗

arXiv2026

Benchmarking Universal Machine Learning Interatomic Potentials for Elastic Property Prediction

Universal machine learning interatomic potentials have emerged as efficient tools for materials simulation, yet their reliability for elastic property prediction remains unclear. Here, we present a systematic benchmark of four uMLIPs -- MatterSim, MACE, SevenNet, and CHGNet -- against first-principles data for nearly 11\,000 elastically stable materials from the Materials Project database. The results show that SevenNet achieves the highest accuracy, MACE and MatterSim balance accuracy with efficiency, while CHGNet performs less effectively overall. To further improve predictive quality, we perform targeted fine-tuning on all four uMLIPs using strained configurations derived from 185 high-error materials. After fine-tuning, CHGNet shows the most substantial improvement in overall accuracy, with MatterSim and SevenNet also benefiting from the fine-tuning, whereas MACE shows limited robustness to this procedure. This work provides quantitative guidance for model selection and data refinement, advancing uMLIPs toward reliable applications in mechanical property prediction.

cond-mat.mtrl-sci↗

arXiv2025

Benchmarking LLMs for Fine-Grained Code Review with Enriched Context in Practice

Code review is a cornerstone of software quality assurance, and recent advances in Large Language Models (LLMs) have shown promise in its automation. However, existing benchmarks for LLM-based code review face three major limitations. Lack of semantic context: most benchmarks provide only code diffs without textual information such as issue descriptions, which are crucial for understanding developer intent. Data quality issues: without rigorous validation, many samples are noisy-e.g., reviews on outdated or irrelevant code-reducing evaluation reliability. Coarse granularity: most benchmarks operate at the file or commit level, overlooking the fine-grained, line-level reasoning essential for precise review. We introduce ContextCRBench, a high-quality, context-rich benchmark for fine-grained LLM evaluation in code review. Our construction pipeline comprises: Raw Data Crawling, collecting 153.7K issues and pull requests from top-tier repositories; Comprehensive Context Extraction, linking issue-PR pairs for textual context and extracting the full surrounding function or class for code context; and Multi-stage Data Filtering, combining rule-based and LLM-based validation to remove outdated, malformed, or low-value samples, resulting in 67,910 context-enriched entries. ContextCRBench supports three evaluation scenarios aligned with the review workflow: hunk-level quality assessment, line-level defect localization, and line-level comment generation. Evaluating eight leading LLMs (four closed-source and four open-source) reveals that textual context yields greater performance gains than code context alone, while current LLMs remain far from human-level review ability. Deployed at ByteDance, ContextCRBench drives a self-evolving code review system, improving performance by 61.98% and demonstrating its robustness and industrial utility. https://github.com/kinesiatricssxilm14/ContextCRBench.

cs.SE↗

arXiv2025

GraphLocator: Graph-guided Causal Reasoning for Issue Localization

The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental yet challenging in automated software engineering due to the semantic gap between issue description and source code implementation. This gap manifests as two mismatches:(1) symptom-to-cause mismatches, where descriptions do not explicitly reveal underlying root causes; (2) one-to-many mismatches, where a single issue corresponds to multiple interdependent code entities. To address these two mismatches, we propose GraphLocator, an approach that mitigates symptom-to-cause mismatches through causal structure discovering and resolves one-to-many mismatches via dynamic issue disentangling. The key artifact is the causal issue graph (CIG), in which vertices represent discovered sub-issues along with their associated code entities, and edges encode the causal dependencies between them. The workflow of GraphLocator consists of two phases: symptom vertices locating and dynamic CIG discovering; it first identifies symptom locations on the repository graph, then dynamically expands the CIG by iteratively reasoning over neighboring vertices. Experiments on three real-world datasets demonstrates the effectiveness of GraphLocator: (1) Compared with baselines, GraphLocator achieves more accurate localization with average improvements of +19.49% in function-level recall and +11.89% in precision. (2) GraphLocator outperforms baselines on both symptom-to-cause and one-to-many mismatch scenarios, achieving recall improvement of +16.44% and +19.18%, precision improvement of +7.78% and +13.23%, respectively. (3) The CIG generated by GraphLocator yields the highest relative improvement, resulting in a 28.74% increase in performance on downstream resolving task.

cs.SE↗

arXiv2025

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents

LLM-powered coding agents, which operate in iterative loops (turns) to solve software engineering tasks, are becoming increasingly powerful. However, their practical deployment is hindered by significant and unpredictable costs. This challenge arises from a combination of factors: quadratically growing token counts with each turn, the high price of models, the large number of turns required for real-world tasks, and the tendency of agents to take inefficient or unnecessary actions. While existing research focuses on optimizing individual turns, the strategic control of the total number of turns remains an underexplored area for managing agent performance and cost. To address this gap, we conduct a comprehensive empirical study on SWE-bench using three state-of-the-art models and evaluate the impact of three distinct turn-control strategies: an unrestricted baseline, a fixed-turn limit with reminders, and a novel dynamic-turn strategy that grants extensions on-demand. Our findings first reveal a fundamental trade-off in the unrestricted setting, where no single model excels across performance, cost, and turn efficiency. We then show that a fixed-turn limit, specifically at the 75th percentile of the baseline, serves as a "sweet spot", substantially reducing costs (by 24%-68%) with minimal impact on solve rates. Most significantly, the dynamic-turn strategy consistently outperforms fixed-limit approaches, achieving comparable or better solve rates while further reducing costs by an additional 12%-24% by intelligently allocating resources only to tasks that need them. This work provides the first systematic analysis of turn-control strategies, offering simple yet effective guidelines for developers to balance cost and efficacy. We demonstrate that dynamic resource allocation is a superior, easy-to-implement approach for deploying powerful yet economically viable coding agents.

cs.SE↗

arXiv2025

RepoMasterEval: Evaluating Code Completion via Real-World Repositories

With the growing reliance on automated code completion tools in software development, the need for comprehensive evaluation benchmarks has become critical. Existing benchmarks focus more on code completion in function and class level by providing text descriptions to prompt the model. By contrast, such descriptive prompt is commonly unavailable in real development and code completion can occur in wider range of situations such as in the middle of a function or a code block. These limitations makes existing evaluation benchmarks poorly align with the practical scenarios of code completion tools. In this paper, we propose RepoMasterEval, a novel benchmark for evaluating code completion models constructed from real-world repositories. Each benchmark datum is generated by masking a code snippet (ground truth) from one source code file with existing test suites. To improve test accuracy of model generated code, we employ mutation testing to measure the effectiveness of the test cases and we manually crafted new test cases for those test suites with low mutation score. Our empirical evaluation on 10 state-of-the-art models shows that test argumentation is critical in improving the accuracy of the benchmark and RepoMasterEval is able to report variance in model performance in real-world scenarios. The deployment of RepoMasterEval also revealed that the benchmark is useful to give accurate feedback during model training and the score is in high correlation with the model's performance in practice.

cs.SE↗

arXiv2025

Scalable Supervision for Software Agents via Patch Reasoning

While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. The reason is twofold: (1) high-coverage tests are naturally rare in the wild, and (2) building and running test sandbox is heavy and fragile. To unlock supervision scaling, we propose R4P, a reasoning-based method that provides scaffold-agnostic rewards. R4P uses a group-wise training objective, enabling it to verify multiple patches against each other's modification and gain a dense reward for supervising agents without executing tests or relying on specific agent trajectories. R4P achieves 72.2% Acc. for verifying patches from SWE-bench, competitive with proprietary models. To show the downstream practical utility of R4P, we design and train an execution-free scaffold, Mini-SE, with pure RL via R4P. Mini-SE achieves 26.2% Pass@1, showing a 10.0% improvement over the original Qwen3-32B, and can be further improved to 32.8% with R4P for test-time scaling on patch selection. The stable scaling curves illustrate that though imperfect, R4P can still reliably support downstream tasks at scale.

cs.CL↗

arXiv2025

CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation

Large language models (LLMs) have demonstrated strong capabilities in code generation, underscoring the critical need for rigorous and comprehensive evaluation. Existing evaluation approaches fall into three categories, including human-centered, metric-based, and LLM-based. Considering that human-centered approaches are labour-intensive and metric-based ones overly rely on reference answers, LLM-based approaches are gaining increasing attention due to their stronger contextual understanding capabilities. However, they generally evaluate the generated code based on static prompts, and tend to fail for complex code scenarios which typically involve multiple requirements and require more contextual information. In addition, these approaches lack fine-grained evaluation for complex code, resulting in limited explainability. To mitigate the limitations, we propose CodeVisionary, the first agent-based evaluation framework for complex code generation. CodeVisionary consists of two stages: (1) Requirement-guided multi-dimensional context distillation stage and (2) Fine-grained scoring and summarization stage. A comprehensive evaluation report is also generated for enhanced explainability. For validation, we construct a new benchmark consisting of 363 samples spanning 37 coding scenarios and 23 programming languages. Extensive experiments demonstrate that CodeVisionary achieves the best performance among three baselines for evaluating complex code generation, outperforming the best baseline with average improvements of 0.217, 0.163, and 0.141 in Pearson, Spearman, and Kendall-Tau coefficients, respectively. The resources of CodeVisionary are available at https://github.com/Eshe0922/CodeVisionary.

cs.SE↗

arXiv2025

An Empirical Study on LLM-based Agents for Automated Bug Fixing

Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in addressing software defects by engaging in development environment interaction, iterative validation and code modification. However, systematic analysis of these agent systems remain limited, particularly regarding performance variations among top-performing ones. In this paper, we examine six repair systems on the SWE-bench Verified benchmark for automated bug fixing. We first assess each system's overall performance, noting the instances solvable by all or none of these systems, and explore the capabilities of different systems. We also compare fault localization accuracy at file and code symbol levels and evaluate bug reproduction capabilities. Through analysis, we concluded that further optimization is needed in both the LLM capability itself and the design of Agentic flow to improve the effectiveness of the Agent in bug fixing.

cs.SE↗