arXiv subjects

Tse-Hsun

Publications and source records attributed to Tse-Hsun.

At least 19 recordsLinked to original sources

arXiv2026

CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications

Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations. We introduce CoAdapt-GUI, a test-time adaptation (TTA) framework that jointly adapts structured workflow context and policy from the agent's own target-app rollouts and rewards. The workflow context retains transferable procedures, failure modes, and verification rules while excluding app-bound source details. This separation allows reusable workflow knowledge to guide adaptation without transferring source-interface state. For policy adaptation, task-context-matched group-relative optimization updates a LoRA adapter on a frozen vision-language model. Across two unseen-app evaluations, CoAdapt-GUI reaches 45.0% on AndroidWorld-Generalization, compared with 37.5% for the reported Policy-Only TTA baseline, and raises AndroidWorld Plus performance from 38.6% to 52.9%. These results show that transfer-constrained workflow context provides substantial gains and that joint policy adaptation further improves held-out performance.

cs.AI↗

arXiv2026

Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework

Autonomous coding agents powered by large language models can now generate code patches directly from bug reports, but a fundamental gap remains: once a patch is produced, no mechanism independently verifies whether it truly resolves the reported problem. Prior work has sought to address this through iterative self-refinement and inference-time scaling, but these approaches either review the patch under the same interpretation that produced it or broaden candidate generation without verifying individual patches, and neither provides an explicit verification signal for assessing patch correctness. We propose RETRACE, a training-free post-generation verification framework that derives such a signal through bidirectional reconstruction and reconciliation. When a coding agent generates a candidate patch for an issue, RETRACE performs forward reconstruction to build an explicit repair rationale from the issue and the agent's trajectory; backward reconstruction then independently infers, from the patch and its trajectory alone and without access to the original issue, a description of the problem the patch appears to address, and compares this reconstruction against the original issue to produce an alignment verdict; a reconciliation stage then checks the consistency between the forward rationale and the patch, diagnoses the source of any misalignment, and either submits the patch or produces targeted revision guidance. Evaluated on SWE-bench Verified with two backbones (GPT-5-mini and MiniMax-2.5), RETRACE lifts Pass@1 by 7.0% and 3.6% respectively on the mini-SWE-agent scaffold, and delivers comparable gains on OpenHands without modification. Ablation experiments show that both the forward and backward stages contribute to the overall improvement and that adding reconciliation yields further gains.

cs.SE↗

arXiv2026

StepReflect: Structured UI Transition Reflection for Mobile GUI Agents

Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal reasoning after each action, which is costly and poorly matched to the structured nature of GUI state transitions. We propose StepReflect, which formulates per-step GUI reflection as supervised structured prediction conditioned on explicit transition specifications and paired visual evidence. StepReflect is trained through a staged pipeline combining supervised fine-tuning, teacher-student distillation, and preference- and reward-based refinement. Offline, the resulting 8B model achieves 82.16% transition-level accuracy on AndroidWorld, exceeding zero-shot GPT-5.2 by 11.83 percentage points under the same structured input. Online, across M3A, Agent-SAMA, MAI-UI-8B, and Seed-2.0-Pro, StepReflect achieves higher task success in three of four agent configurations and remains within one successful task of the GPT-5.2 Reflection Agent in the fourth. It also reduces paid API charges relative to GPT-based reflection in all four configurations. These results establish StepReflect as a practical, locally deployable alternative to repeated frontier-model reflection for long-horizon mobile GUI agents.

cs.AI↗

arXiv2026

Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents

Long-horizon coding agents accumulate hundreds of actions and observations in their trajectories, yet nothing in this record indicates which observations still describe the repository as it currently stands. Before every decision, the model must implicitly infer the execution status from raw history, and when this inference falls short, the agent acts on outdated file contents or re-executes work whose results are still valid. We propose Ledger, a deterministic runtime layer that distills an agent's completed interactions into an explicit execution state: what has been observed, what has been modified, and what has been attempted. Ledger keeps this state in an online execution ledger and applies it at two boundaries of every step. Before the model acts, an inform path appends a compact runtime state view to the prompt; before a proposed command runs, a govern path checks it against the ledger, returning still-valid earlier results in place of re-execution and flagging likely-redundant repetition. The layer adds no language-model calls and wraps an otherwise unmodified agent. Across all 500 SWE-bench Verified instances, Ledger raises Pass@1 from 56.2% to 64.2% with GPT-5 mini and from 75.8% to 81.0% with MiniMax M2.5, while cutting total cost by 28.9% and 31.8%. Attached to OpenAI Codex, it adds 3.4 percentage points of Pass@1 at 24.4% lower cost. Ablations attribute most of the resolution gain to govern and most of the efficiency gain to inform, with their combination performing best. What long-horizon agents lack, we conclude, is not a shorter view of their history but an explicit account of their own execution state.

cs.SE↗

arXiv2026

Retrieval-Oriented Code Representations in Agentic Bug Localization

LLM-based agents are increasingly being used to support software development, yet their performance in repository-level tasks depends on retrieving the right code context. Existing studies have explored file-level localization using traditional information retrieval over file paths and raw source code. However, the role of textual code representations in retrieval and localization remains underexplored. We study file-level bug localization as a representation-driven retrieval problem. Across the Long Code Arena (LCA) and SWE-bench Verified (SWE) datasets, we compare five code representations: file paths, raw source code, and three LLM-generated textual representations. Our experiments include lexical, semantic, and LLM-based retrieval, followed by LLM-based post-retrieval ranking. We quantify the cost incurred by a representation through the representation footprint. We find that the choice of code representation affects both localization effectiveness and cost. Role-aware summaries outperform file-path representations by up to 40% Hit@5 while requiring a representation footprint 10.4 to 20.9x smaller than raw source code. Combining complementary representation results and ranking retrieved candidates with an LLM provides further gains of up to 31.9% and 42.0%, respectively. Overall, role-aware summaries provide the best cost-effectiveness trade-off, while raw source code offers effectiveness in some settings at a significantly higher cost. A case study with Agentless reveals the utility of our techniques within a well-known pipeline, reaching 94% Hit@6 on file localization (+4.7% against the baseline). Our findings suggest that code representation should be treated as a first-class design choice in agentic localization pipelines, guided by pipeline stage and cost-accuracy requirements.

cs.SE↗

arXiv2026

Rethinking Code Performance Benchmarks for LLMs

Many function-level performance benchmarks have been proposed to evaluate whether large language models (LLMs) can generate efficient programs. However, results on these benchmarks often show that LLM-generated implementations have little or no execution-time difference from canonical solutions. In this paper, we revisit four popular benchmarks: EffiBench, Enamel, EvalPerf, and Mercury. We evaluate 1,538 tasks under more rigorous setting by running each task 30 times and assessing the runtime differences between the canonical solutions and benchmark-provided performant implementations with statistical testing. With the benchmark-provided test suites, only 6.11% of the performant implementations are significantly faster than the canonical solutions. In a manual analysis of 308 non-significant tasks, 99 performant implementations contain no meaningful performance change, while 209 contain potential performance improvements that are not exposed by the original tests. These results suggest that the main limitation is not only the evaluation method, but also the limited sufficiency of the benchmark-provided performance tests. To address this limitation, we propose an LLM-based multi-agent framework to generate performance-oriented tests that expose runtime differences more effectively than the original tests. The framework uses three separate agents to generate, diagnose, and repair deterministic tests that preserve functional correctness while better exposing performance differences. Across 1,345 benchmark tasks for which the original tests found no significant performance difference, tests generated by our framework with DeepSeek-v3.1 and GPT-4o reveal statistically significant improvements in 24.01% and 25.43% of the tasks, respectively, outperforming the SOTA LLM-based performance test generation method.

cs.SE↗

arXiv2026

Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair

Bug reports serve as task specifications for repository-level automated program repair (APR) agents, but they often describe only the observed failure and omit repair-relevant information such as the failure-inducing behavior, behavioral requirement, and implementation scope. As a result, a repair agent may inspect irrelevant code, infer an incorrect requirement, or generate a patch that addresses the reported symptom without restoring the intended repository behavior. We present TrajSpec, a trajectory-guided approach for repository-supported bug report specification refinement. Given an original report and a pre-fix repository, TrajSpec runs a trajectory-collection agent and uses the resulting unverified trajectory as a source of trajectory-derived specification evidence. It organizes this evidence into a three-level representation consisting of a high-level interpretation of the issue, diagnostic findings supporting that interpretation, and concrete repository observations. TrajSpec then generates a draft refined report and applies repository-based review to remove unsupported claims, revise uncertain claims, and add repository-supported details. We evaluate TrajSpec on all 300 SWE-Bench Lite instances using Mini-SWE-Agent V2. TrajSpec's refined reports improve Pass@1 from 41.00% to 59.67% with GPT-5-mini and from 54.67% to 64.33% with MiniMax M2.5. On a stratified sample of 100 instances, TrajSpec's refined reports also improve Pass@1 from 41.00% to 71.00% with Agentless and from 47.00% to 72.00% with AutoCodeRover. Ablation results show that removing repository-based review or the hierarchical evidence representation reduces Pass@1 from 59.67% to 48.00% and 47.67%, respectively. Overall, TrajSpec provides actionable repository-supported context that consistently improves repair performance.

cs.SE↗

arXiv2026

CI-Repair-Bench: A Repository-Aware Benchmark for Automated Patch Validation via CI Workflows

Continuous Integration (CI) enforces repository-level correctness through multi-stage workflows and is central to modern software development, yet diagnosing and repairing CI failures remains challenging. Unlike traditional program repair, CI failures frequently involve non-code artifacts, environment and dependency issues, noisy execution logs, and workflow-level constraints. Existing program repair benchmarks fall short in this setting: they are largely test-centric, restrict repairs to source code, assume fixed execution environments, and evaluate under simplified CI workflows that do not reflect real repository-level validation. We introduce CI-Repair-Bench, a benchmark for CI-verified, repository-level program repair constructed from real GitHub Actions executions. It contains 567 CI failure instances from 103 repositories and evaluates repair correctness exclusively through full CI re-execution under original workflows. Failures are categorized into 12 CI error types, enabling fine-grained, error-type-aware evaluation. To demonstrate benchmark usage, we include a reference CI repair workflow that analyzes CI logs to localize faults and generate candidate patches. Empirical results show that automated repair is most effective for localized, tool-enforced failures such as formatting and linting, while environment, dependency, and configuration-related failures remain challenging; the best-performing LLM achieves an 18.9% repair success rate. CI-Repair-Bench provides a realistic evaluation foundation for advancing research on CI-native automated program repair.

cs.SE↗

arXiv2026

Probe to Generate: Program Variant-Guided Test Augmentation for Repository-Level Repair Benchmarks

Test-based benchmarks such as SWE-bench have become a standard basis for evaluating automated issue resolution agents, deeming a patch correct if it passes a provided regression test suite. In practice, weak test suites can admit plausible but semantically incorrect patches, inflating reported agent performance. We present \tool, a test augmentation framework that uses semantically modified program variants as behavioral probes to identify and close gaps in benchmark test suites. Variants of the reference patch that survive the original tests reveal under-constrained behaviors, which then guide targeted regression test generation. Each generated test is retained only if it passes on the reference patch, fails on at least one surviving variant, and remains robust under behavior-preserving transformations. On SWE-bench Verified, 77% of instances admit at least one surviving variant. \tool generates 1,014 validated tests across 211 instances, increasing patch-region line and branch coverage by 10.8 and 9.5 percentage points. Re-evaluating the top-10 repair agents with the augmented suites reduces resolved rates by 4.2%-9.0%, showing that many previously accepted patches exploit benchmark test gaps rather than fully satisfying the intended repair semantics. These findings demonstrate that benchmark evaluation is not solely a patch-generation problem but also a test-strength problem.

cs.SE↗

arXiv2026

Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents

Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However, this reactive design provides no explicit structure or persistent state within the agent's memory, making long-horizon reasoning challenging. As a result, SE agents struggle to maintain a coherent understanding across reasoning steps, adapt their hypotheses as new evidence emerges, or incorporate execution feedback into the mental reasoning model of the system state. In this position paper, we argue that, to further advance SE agents, we need to move beyond reactive behavior toward a structured, state-aware, and execution-grounded reasoning. We outline how explicit structure, persistent and evolving state, and the integration of execution-grounded feedback can help SE agents perform more coherent and reliable reasoning in long-horizon tasks. We also provide an initial roadmap for developing next-generation SE agents that can more effectively perform real-world tasks.

cs.SE↗

arXiv2026

SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring

Large Language Models (LLMs) have recently attracted wide interest for tackling software engineering tasks. In contrast to code generation, refactoring demands precise, semantics-preserving edits that improve program structure, which also makes automated evaluation challenging. However, existing refactoring benchmarks commonly suffer from three shortcomings: limited coverage of refactoring scenarios, the inclusion of instances that mix refactoring with unrelated changes, and insufficient repository-level context for realistic assessment. To mitigate these issues, we introduce SWE-Refactor, a new benchmark for LLM-based code refactoring. SWE-Refactor comprises 1,099 developer-written, behavior-preserving refactorings mined from 18 Java projects, including 922 atomic and 177 compound instances. Each instance is validated via compilation, test execution, and automated refactoring detection tools to ensure correctness. We evaluate nine widely used LLMs on SWE-Refactor, covering models such as GPT-4o-mini, DeepSeek-V3, and CodeLLaMa, to provide representative reference results. Our results show that complex and compound refactorings remain the primary source of failures; notably, an OpenAI Codex agent achieves only 39.4% success on compound instances. We release SWE-Refactor and all evaluation results to facilitate future research on LLM-based code refactoring.

cs.SE↗

arXiv2026

From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair

Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories contain many related issues with shared structure or constraints. Existing methods typically rely on forward exploration, which operates under outcome uncertainty, incurs substantial inference-time overhead, and can drift from the final correct patch. We propose Conditional Reasoning Distillation (ConRAD), which leverages in-repository resolved issues by reconstructing repair reasoning backward from verified patches and distilling outcome-consistent, stage-wise repair reasoning plans. Injected at inference time, these plans guide fault localization and patch generation, replacing open-ended exploration with constrained inference without fine-tuning or search. On SWE-Bench Lite, ConRAD improves Pass@1 by 10.4\% (GPT-4o), 8.6\% (DeepSeek-V3), and 10.3\% (GPT-5), demonstrating a scalable inference-time alternative to forward exploration for long-horizon APR.

cs.SE↗

arXiv2025

MobileUPReg: Identifying User-Perceived Performance Regressions in Mobile OS Versions

Mobile operating systems (OS) are frequently updated, but such updates can unintentionally degrade user experience by introducing performance regressions. Existing detection techniques often rely on system-level metrics (e.g., CPU or memory usage) or focus on specific OS components, which may miss regressions actually perceived by users -- such as slower responses or UI stutters. To address this gap, we present MobileUPReg, a black-box framework for detecting user-perceived performance regressions across OS versions. MobileUPReg runs the same apps under different OS versions and compares user-perceived performance metrics -- response time, finish time, launch time, and dropped frames -- to identify regressions that are truly perceptible to users. In a large-scale study, MobileUPReg achieves high accuracy in extracting user-perceived metrics and detects user-perceived regressions with 0.96 precision, 0.91 recall, and 0.93 F1-score -- significantly outperforming a statistical baseline using the Wilcoxon rank-sum test and Cliff's Delta. MobileUPReg has been deployed in an industrial CI pipeline, where it analyzes thousands of screencasts across hundreds of apps daily and has uncovered regressions missed by traditional tools. These results demonstrate that MobileUPReg enables accurate, scalable, and perceptually aligned regression detection for mobile OS validation.

cs.SE↗

arXiv2025

Crash Report Enhancement with Large Language Models: An Empirical Study

Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause explanations, and repair suggestions. We study two enhancement strategies: Direct-LLM, a single-shot approach that uses stack-trace context, and Agentic-LLM, an iterative approach that explores the repository for additional evidence. On a dataset of 492 real-world crash reports, LLM-enhanced reports improve Top-1 problem-localization accuracy from 10.6% (original reports) to 40.2-43.1%, and produce suggested fixes that closely resemble developer patches (CodeBLEU around 56-57%). Both our manual evaluations and LLM-as-a-judge assessment show that Agentic-LLM delivers stronger root-cause explanations and more actionable repair guidance. A user study with 16 participants further confirms that enhanced reports make crashes easier to understand and resolve, with the largest improvement in repair guidance. These results indicate that supplying LLMs with stack traces and repository code yields enhanced crash reports that are substantially more useful for debugging.

cs.SE↗

arXiv2025

Screencast-Based Analysis of User-Perceived GUI Responsiveness

GUI responsiveness is critical for a positive user experience in mobile applications. Even brief delays in visual feedback can frustrate users and lead to negative reviews. However, detecting and quantifying such user-perceived delays remains challenging, especially in industrial testing pipelines that evaluate thousands of apps daily across diverse devices and OS versions. Existing techniques based on static analysis or system metrics, while useful, may not accurately capture user-perceived issues or scale effectively. In this experience paper, we present \tool, a lightweight and black-box technique that measures GUI responsiveness directly from mobile screencasts -- video recordings captured during automated GUI testing. \tool detects user interactions and visual delays, helping developers identify GUI performance issues that affect the user experience. It uses computer vision to detect user interactions and analyzes frame-level visual changes to compute two key metrics: response time (from user action to first visual feedback) and finish time (until visual feedback stabilizes). We evaluate \tool on a manually annotated benchmark of 2,458 interactions from 64 popular Android apps. \tool achieves 0.96 precision and 0.93 recall in detecting interactions, and measures response and finish times within 50\,ms and 100\,ms error, respectively, for over 89\% of interactions. The tool has been deployed in an industrial testing pipeline and analyzes thousands of screencasts daily, uncovering responsiveness issues missed by traditional tools and improving performance debugging efficiency.

cs.SE↗

arXiv2025

Agent-SAMA: State-Aware Mobile Assistant

Mobile Graphical User Interface (GUI) agents aim to autonomously complete tasks within or across apps based on user instructions. While recent Multimodal Large Language Models (MLLMs) enable these agents to interpret UI screens and perform actions, existing agents remain fundamentally reactive. They reason over the current UI screen but lack a structured representation of the app navigation flow, limiting GUI agents' ability to understand execution context, detect unexpected execution results, and recover from errors. We introduce Agent-SAMA, a state-aware multi-agent framework that models app execution as a Finite State Machine (FSM), treating UI screens as states and user actions as transitions. Agent-SAMA implements four specialized agents that collaboratively construct and use FSMs in real time to guide task planning, execution verification, and recovery. We evaluate Agent-SAMA on two types of benchmarks: cross-app (Mobile-Eval-E, SPA-Bench) and mostly single-app (AndroidWorld). On Mobile-Eval-E, Agent-SAMA achieves an 84.0% success rate and a 71.9% recovery rate. On SPA-Bench, it reaches an 80.0% success rate with a 66.7% recovery rate. Compared to prior methods, Agent-SAMA improves task success by up to 12% and recovery success by 13.8%. On AndroidWorld, Agent-SAMA achieves a 63.7% success rate, outperforming the baselines. Our results demonstrate that structured state modeling enhances robustness and can serve as a lightweight, model-agnostic memory layer for future GUI agents.

cs.AI↗

arXiv2025

Studying the Impact of Early Test Termination Due to Assertion Failure on Code Coverage and Spectrum-based Fault Localization

An assertion is commonly used to validate the expected programs behavior (e.g., if the returned value of a method equals an expected value) in software testing. Although it is a recommended practice to use only one assertion in a single test to avoid code smells (e.g., Assertion Roulette), it is common to have multiple assertions in a single test. One issue with tests that have multiple assertions is that when the test fails at an early assertion (not the last one), the test will terminate at that point, and the remaining testing code will not be executed. This, in turn, can potentially reduce the code coverage and the performance of techniques that rely on code coverage information (e.g., spectrum-based fault localization). We refer to such a scenario as early test termination. Understanding the impact of early test termination on test coverage is important for software testing and debugging, particularly for the techniques that rely on coverage information obtained from the testing. We conducted the first empirical study on early test termination due to assertion failure (i.e., early test termination) by investigating 207 versions of 6 open-source projects. We found that a nonnegligible portion of the failed tests (19.1%) is early terminated due to assertion failure. Our findings indicate that early test termination harms both code coverage and the effectiveness of spectrum-based fault localization. For instance, after eliminating early test termination, the line/branch coverage is improved in 55% of the studied versions, and improves the performance of two popular SBFL techniques Ochiai and Tarantula by 15.1% and 10.7% compared to the original setting (without eliminating early test termination) in terms of MFR, respectively.

cs.SE↗

arXiv2025

RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation

When using LLMs to address Non-Functional Requirements (NFRs), developers may behave differently (e.g., expressing the same NFR in different words). Robust LLMs should output consistent results across these variations; however, this aspect remains underexplored. We propose RobuNFR for evaluating the robustness of LLMs in NFR-aware code generation across four NFR dimensions: design, readability, reliability, and performance, using three methodologies: prompt variation, regression testing, and diverse workflows. Our experiments show that RobuNFR reveals robustness issues in the tested LLMs when considering NFRs in code generation. Specifically, under prompt variation, including NFRs leads to a decrease in Pass@1 by up to 39 percent and an increase in the standard deviation from 0.48 to 2.48 compared to the baseline without NFRs (i.e., Function-Only). While incorporating NFRs generally improves overall NFR metrics, it also results in higher prompt sensitivity. In regression settings, some LLMs exhibit differences across versions, with improvements in one aspect (e.g., reduced code smells) often accompanied by regressions in another (e.g., decreased correctness), revealing inconsistencies that challenge their robustness. When varying workflows, the tested LLMs show significantly different NFR-aware code generation capabilities between two workflows: (1) integrating NFRs and functional requirements into the initial prompt and (2) enhancing Function-Only-generated code with the same NFR.

cs.SE↗