arXiv subjects

Shaowei Wang

Publications and source records attributed to Shaowei Wang.

At least 19 recordsLinked to original sources

arXiv2026

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental crashes and reward hacking corrupt outcome signals, while train-inference discrepancies decouple rollout behavior from policy updates. To address this, we present LEGO-RL, a framework that bridges native coding-agent harnesses with scalable policy-gradient optimization without modifying their internal control flow. LEGO-RL is built upon three pillars: (1) faithful optimization via in-process LLM proxying that captures raw generation streams for token-level alignment and robust trainer-side log-probability recomputation, even under harness-side compaction or re-serialization; (2) reliable execution via scalable sandbox orchestration featuring image caching and stage-wise defenses to mitigate reward hacking; and (3) observable training through an integrated plugin that automates validation and monitoring, paired with a Live UI for granular trajectory diagnostics. We evaluate LEGO-RL by training the sparse MoE model Qwen3.5-35B-A3B with GSPO across three native coding-agent harnesses. LEGO-RL improves Qwen3.5-35B-A3B across OpenHands SDK (64.0% to 70.4%), Claude Code (62.4% to 68.2%), and OpenCode (57.2% to 66.6%) on SWE-bench Verified, while maintaining a rollout-training probability correlation above 0.99.

cs.AI↗

arXiv2026

A unified reconstruction algorithm for reduced-frame structured illumination microscopy

Reduced-frame structured illumination microscopy (SIM) is attractive for live-cell imaging because it can improve temporal throughput and reduce photobleaching, but incomplete phase sampling makes reconstruction unstable and computationally demanding. Here we present URA-SIM, a unified reduced-acquisition framework that turns fixed reduced-frame measurements into pipeline- compatible raw stacks through model-consistent phase-domain completion. Instead of solving a large object-level inverse problem or replacing established SIM reconstruction, URA-SIM estimates the missing phase content on the low-dimensional phase-harmonic manifold required by the target modality and then delegates order separation and image formation to classical reconstruction pipeline. This design combines three practical advantages: fidelity from the SIM forward structure, lightweight online computation, and direct compatibility with existing reconstruction workflows. For 2D-SIM, URA-SIM uses the first-harmonic phase structure of three-phase SIM to estimate a shared zero-order field and complete missing phase samples by direction-wise harmonic fitting. On calibration and biological 2D-SIM data, reduced-frame reconstructions preserve resolvable structures and remain competitive on COS7 mitochondria comparison data. In live-cell COS7 mitochondria imaging, URA-SIM reconstructs each time point from five acquired raw frames and resolves mitochondrial cristae across different temporal sampling regimes. Experiments on 3D-SIM and nonlinear SIM further show that the same design principle can be transferred when the phase model and reconstruction-pipeline interface are adapted to the target modality. These results support URA-SIM as a transparent, model-consistent and computationally lightweight route from fixed reduced-frame acquisition to classical SIM reconstruction workflows.

physics.optics↗

arXiv2026

Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy

Local differential privacy (LDP) protocols are vulnerable to poisoning attacks. Existing research have proposed efficient defense strategies for single-item users. However, in practice, a user may possess multiple items. The defense against poisoning attacks for multi-item users is challenging, because due to larger output spaces, the adversary can conduct more powerful attacks without being detected. In this paper, we address the robust sparse vector mean estimation problem, in which each user has a vector with $m$ nonzero coordinates. We propose Randomized Projection with Clipping (RPC). Firstly, the server sends a random binary vector to each user. The user then projects its local data on the vector, and clip the value to restrict the attacker's capability. To handle clipping bias, we propose a correction method based on a careful analysis that gives an exact expression of the bias. As a result, bias-variance tradeoff is no longer needed, thus the clipping threshold can be further reduced to shrink the output space and enhance robustness. We provide a rigorous theoretical guarantee of the estimation error under all possible attacks. Numerical experiments show that under trusted environments, our new method achieves comparable or better performance than existing methods, indicating that our method is already an efficient estimator in its own right. Under untrusted environments, our method is also significantly more robust to poisoning attacks.

stat.ML↗

arXiv2026

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a major challenge: even the frontier models evaluated on ProgramBench fully resolve fewer than 1% of tasks. One obstacle is the lack of scalable training environments for this from-scratch setting, spanning the whole software engineering life cycle, as existing environment-construction frameworks focus only on a single phase in software development. To address this gap, we introduce MindForge, an automated pipeline that converts open-source command-line programs into source-free environments that expose only a compiled reference executable and its documentation. Using MindForge, we construct training environments from repositories disjoint from those in ProgramBench, and curate a high-quality data recipe consisting of program synthesis trajectories using GLM-5.2 as the teacher agent. Fine-tuning Qwen3.6-27B on these trajectories increases its ProgramBench average test pass rate from 37.98% to 49.51%, achieving performance comparable to substantially larger frontier models. Moreover, the fine-tuned model consistently improves over the base model across all seven unseen software engineering benchmarks, spanning long-horizon repository generation and translation, bug fixing, feature implementation, and cross-language issue resolution, with absolute gains of 31.00 points on RepoZero-C2Rust, 14.16 on DeepSWE, 10.70/4.56 on NL2Repo-Bench (with/without tests), 5.04 on SWE-bench Verified, 5.93 on SWE-bench Pro, 5.22 on SWE-bench Multilingual, and 4.94 on FeatBench.

cs.SE↗

arXiv2026

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this gap: given only natural-language documentation and an execute-only binary as a behavioral oracle, even frontier models solve fewer than 1% of instances. Existing frameworks conflate documentation reading, behavioral exploration, and code synthesis into a single pass, causing agents to probe insufficiently, lose behavioral intent as context drifts, and propagate early misinterpretations into the final implementation. Inspired by classical requirements engineering, we argue that behavioral specification elicitation should be a first-class phase that precedes implementation. We present SpecFirst, a two-stage framework that forces the specification elicitation before code synthesis. A dedicated spec agent first probes the binary and combines observations with documentation into a structured specification. Next, a code synthesis agent then uses this specification to drive implementation. This decomposition resolves documentation ambiguities before coding begins and provides a stable behavioral reference throughout synthesis. We evaluate SpecFirst on all 200 ProgramBench instances across four models spanning two families and an order of magnitude of capability. SpecFirst consistently outperforms the single-loop baseline, improving test pass rates by 6.9%-21.3% and binary exploration coverage by 9.4%-18.5%, all statistically significant. Behavioral analysis on code synthesis further shows that a prior specification enables earlier and more sustained code construction. Our results demonstrate that an explicit requirements-engineering phase is an effective paradigm for from-scratch program construction.

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

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

Coding agents increasingly generate pull requests (PRs) for real-world software issues, yet one-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or revision. We introduce \textbf{SWE-Review}, a framework for closing this loop with agentic code review. Given an issue and an AI-generated PR, a reviewer agent explores the repository, decides whether the PR should be accepted, and provides structured feedback for revision. We evaluate this setting with our proposed \textbf{SWE-Review-Bench} to measure both review correctness and downstream revision usefulness. We further curate \textbf{SWE-Review-Traj} dataset to study broader applications of agentic review and fill the data-scarcity gap for open reviewer training. Experiments show that agentic review continuously improves PRs through a generate-review-revise loop, outperforms single-turn fixed-context review in both decision accuracy and resolve rate after revision, transfers beyond review to improve issue-resolution models, and enables effective and efficient test-time scaling. These results position agentic code review as a practical mechanism for moving AI coding agents from one-shot PR generation toward closed-loop issue resolution.

cs.SE↗

arXiv2026

Evaluating LLMs on Java Code Snippet Adaptation Using a Mutation-Injection Framework

Background: Developers frequently reuse code by copying fragments and adapting them to fit new contexts. Existing benchmarks for evaluating large language models (LLMs) on code adaptation either rely on explicit step-by-step instructions, cover only narrow change types such as variable wiring, or operate exclusively at function-level granularity. It remains unknown how well LLMs can adapt code fragments without explicit edit guidance when the required changes are varied and controlled. Objective: We investigate instruction-free code snippet adaptation in which an LLM must adapt a code fragment to fit its target context without any explicit edit guidance. We study three dimensions: which adaptation types are hardest (RQ1), how performance scales with adaptation complexity (RQ2), and how much surrounding context the model needs (RQ3). Method: We will construct a dataset of Java code fragments from open-source repositories with strong test coverage and apply a taxonomy of adaptation operators, derived from empirical findings on how developers adapt copied code, using a mutation-injection framework. Working at the code fragment level and controlling the injected changes lets us know exactly what adaptations the model must perform. The unmutated fragment serves as a plausible reference for the changes the model needs to make. LLMs will be evaluated on instruction-free adaptation tasks across three context granularity levels. Correctness will be measured primarily via test-suite re-insertion, complemented by mutation-level inspection.

cs.SE↗

arXiv2026

Multi-tier Differential Private Query Release

Answering statistical queries over sensitive data under differential privacy (DP) is a common task in many settings, including databases, mobile computing, and data markets. In these scenarios, multiple analysts may issue the same query, while receiving answers generated under different privacy budgets due to differences in trust levels or willingness to pay. Existing approaches for such multi-tier DP queries either incur excessive cumulative privacy loss or suffer from suboptimal utility. In this paper, we propose a framework for multi-tier DP query release that simultaneously bound the cumulative privacy loss by the maximum privacy budget among all queries and achieve optimal utility comparable to that of single-tier mechanisms. Our framework applies to different classes of DP mechanisms. For noise-adding mechanisms (e.g., count queries with the two-sided Geometric mechanism in the curator model), we develop a general solution based on the characteristic functions of noise distributions. For other mechanisms (e.g., count queries under the local DP model with the Subset mechanism), we design mechanism-specific primitives for budget transformation and introduce a template-based strategy that attains optimal utility across different privacy regimes. Experimental results demonstrate the effectiveness of our framework.

cs.CR↗

arXiv2026

Hierarchical ODE: Learning Continuous-Time Physical Prototypes for Early Link Failure Detection

Time series prototype learning is fundamentally challenged by observational ambiguity. Discrete architectures fail to resolve this, as they lack the capacity to decouple stochastic noise from continuous dynamics. Furthermore, rigid closed-set assumptions fail to capture unseen diversity. To address these limitations, we propose a hierarchical ordinary differential equation clustering network, which utilizes neural ordinary differential equation to model latent state evolution as a continuous integral curve. This formulation enforces temporal continuity to effectively disentangle smooth feature trends from stochastic noise, while our adaptive hierarchical mechanism autonomously determines the appropriate number of prototypes without rigid prior constraints. Validated on the early link failure detection task with irregularly sampled time series, the proposed method effectively extracts underlying physical prototypes, thereby enabling robust failure detection. Our code is available at https://github.com/NJ-LNN/Hierarchical-ODE.

cs.LG↗

arXiv2026

Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment

LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is prohibitively expensive to label manually and impossible to verify through tests alone. We propose an agentic judging pipeline using a strong LLM as a scalable proxy for expert architectural evaluation, comprising two judges: the Architecture Complexity Judge (ACJ), which estimates codebase-specific architectural understanding a task demands, and the Architecture Quality Judge (AQJ), which evaluates patch conformance to repository-specific architectural conventions via source-grounded rubrics. Fine-tuning Qwen3-8B/14B/32B on 3,360 curated instances achieves resolved rates of up to 27.2% on SWE-bench Verified - up to 540% over the base model and 256% over unfiltered fine-tuning. Meanwhile, the trained models achieve strong cross-language generalization and consistent improvements in architectural patch quality.

cs.SE↗

arXiv2026

Think Harder and Don't Overlook Your Options: Revisiting Issue-Commit Linking with LLM-Assisted Retrieval

Linking issue reports to the commits that resolve them is essential for software traceability, maintenance, and evolution. Accurate issue-commit links help developers to understand system changes and the rationale behind them. While numerous automated techniques have been proposed, ranging from heuristic and feature-based approaches to modern deep learning and large language model approaches, our goal is to evaluate these techniques to determine which are most effective and efficient. In this study, we revisit several established issue-commit link recovery techniques, including BTLink, EasyLink, FRLink, RCLinker, and Hybrid-Linker, and assess their performance for reranking issue-commit links. We first evaluate different retrieval methods (BM25, BM25L, SBERT-Semantic Search, ANNOY, LSH, HNSW) for their ability to efficiently retrieve relevant commits, reducing the candidate set that must be considered by more computationally expensive models. Using the best retrieval methods, we then investigate the reranking effectiveness of different machine learning-based techniques, including traditional machine learning models, a cross-encoder, and large language models (ChatGPT, Qwen, Gemma, Llama), to refine the reranking of candidate commits and improve precision. Finally, we compare the effectiveness of these techniques. Our results show that dense retrieval methods outperform sparse retrieval approaches in identifying relevant commits and that combining dense and sparse retrieval can improve recall. Additionally, we find that traditional machine learning-based reranking techniques achieve higher performance than LLM-based approaches. Our results highlight that retrieval-based pipelines remain a practical and effective solution for large-scale issue-commit linking, and that simpler models should be carefully considered before adopting computationally expensive LLM-based approaches.

cs.SE↗

arXiv2026

Source localization realizes single frame super-resolution for fluorescence imaging

Existing super-resolution microscopy is often constrained by inherent trade-offs between resolution, acquisition speed, phototoxicity, and hardware complexity. Computational post-processing approaches offer a promising alternative, but they typically suffer from linearity distortion, high computational cost, reliance on pre-training data, or reconstruction artifacts. Here, we present Source Localization (SoLo), a novel single-frame super-resolution algorithm for fluorescence imaging without these limitations. Built on the principle of inferring fluorescent source positions via sampling-detection strategy, SoLo achieves non-iterative, parallelizable computation, enabling real-time live-cell imaging with high spatiotemporal resolution. The intensity linearity preservation of SoLo makes it compatible with quantitative analysis such as calcium imaging and fluorescence resonance energy transfer. We further extended this framework to 3D-SoLo for volumetric imaging and nonlinear SoLo (NL-SoLo) for high-density fluorescence fluctuation imaging. With its ease of parameter tuning and compatibility with existing imaging systems, SoLo offers an accessible solution for ordinary labs, enabling diverse biomedical imaging applications.

physics.optics↗

arXiv2026

When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation

The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. While retrieval-augmented generation (RAG) is commonly used to provide up-to-date API specifications, "context-memory conflict" arises when external instructions contradict a model's internal parametric knowledge. This paper presents a systematic empirical study of LLM code generation under API evolution (e.g., API deprecation, API modification, and API addition), by constructing a benchmark of 270 real-world updates from eight Python libraries. We evaluate four LLM families of 11 models. Our results show that without comprehensive documentation, LLMs struggle to prioritize external context, averaging only 42.55% of generated code examples are executable in the target environment. While structured documentation and larger model scales improve LLMs' ability to update adoption, they do not fully resolve executability issues with a low 66.36% executable rate. In addition, reasoning-based strategies (e.g., Self-Reflection) significantly boost LLMs' performance with 11% improvement on executable rate. Our findings highlight the persistence of outdated patterns from LLMs, even when API update specifications are provided, and emphasize the need for evolution-aware benchmarks and techniques.

cs.SE↗

arXiv2026

Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding

Static program slicing is a fundamental software engineering technique for isolating code relevant to specific variables. While recent learning-based approaches using language models (LMs) show promise in automating slice prediction, they suffer from inaccurate dependency modeling and unconstrained generation, where LMs fail to capture precise data flow relations and produce slices containing hallucinated tokens and statements. To address these challenges, we propose Sliceformer, a novel approach that reformulates static program slicing as a sequence-to-sequence task using small language models such as CodeT5+. Sliceformer introduces two key innovations that directly target the identified limitations. First, to improve dependency modeling, we design dataflow-aware pretraining objectives that leverage data flow graphs (DFG) to teach models data dependencies through dataflow-preserving statement permutation and dataflow-aware span corruption. Second, to eliminate hallucination, we develop a constrained decoding mechanism that enforces both lexical and syntactic constraints. We evaluate Sliceformer on Java and Python program slicing benchmarks, demonstrating consistent improvements over state-of-the-art baselines with up to 22% gain in ExactMatch.

cs.SE↗

arXiv2026

REAgent: Requirement-Driven LLM Agents for Software Issue Resolution

Issue resolution aims to automatically generate patches from given issue descriptions and has attracted significant attention with the rapid advancement of large language models (LLMs). However, due to the complexity of software issues and codebases, LLM-generated patches often fail to resolve corresponding issues. Although various advanced techniques have been proposed with carefully designed tools and workflows, they typically treat issue descriptions as direct inputs and largely overlook their quality (e.g., missing critical context or containing ambiguous information), which hinders LLMs from accurate understanding and resolution. To address this limitation, we draw on principles from software requirements engineering and propose REAgent, a requirement-driven LLM agent framework that introduces issue-oriented requirements as structured task specifications to better guide patch generation. Specifically, REAgent automatically constructs structured and information-rich issue-oriented requirements, identifies low-quality requirements, and iteratively refines them to improve patch correctness. We conduct comprehensive experiments on three widely used benchmarks using two advanced LLMs, comparing against five representative or state-of-the-art baselines. The results demonstrate that REAgent consistently outperforms all baselines, achieving an average improvement of 17.40% in terms of the number of successfully-resolved issues (% Resolved).

cs.SE↗

arXiv2026

Typify: A Lightweight Usage-driven Static Analyzer for Precise Python Type Inference

Python's dynamic type system, while offering significant flexibility and expressiveness, poses substantial challenges for static analysis and automated tooling, particularly in unannotated or partially annotated codebases. Existing type inference approaches often depend on existing type annotations or on deep learning models that require extensive training corpora and considerable computational resources, resulting in limited scalability and reduced interpretability. We introduce Typify, a lightweight, usage-driven static analysis engine designed to infer precise and contextually relevant type information without relying on statistical learning or large datasets. Typify integrates symbolic execution with iterative fixpoint analysis and a context-matching retrieval system to propagate and predict type information across entire projects. By constructing and traversing dependency graphs in an execution-aware manner, Typify accurately connects function calls to their definitions and infers usage-based type semantics, even in complex, interdependent modules. We evaluate Typify on a diverse corpus of real-world Python repositories, including the ManyTypes4Py and Typilus datasets, benchmarking its effectiveness in predicting types of variables, arguments, and return statements. Results from the evaluation show that Typify consistently matches or surpasses state-of-the-art deep learning-based systems such as Type4Py and HiTyper, as well as industry-standard static type inference tools like Pyre. Our findings demonstrate that usage-driven, retrieval-based inference can match or exceed the accuracy of data-driven methods, offering a practical, interpretable, and computationally efficient alternative for large and evolving Python codebases.

cs.SE↗

arXiv2026

A Survey of Code Review Benchmarks and Evaluation Practices in Pre-LLM and LLM Era

Code review is a critical practice in modern software engineering, helping developers detect defects early, improve code quality, and facilitate knowledge sharing. With the rapid advancement of large language models (LLMs), a growing body of work has explored automated support for code review. However, progress in this area is hindered by the lack of a systematic understanding of existing benchmarks and evaluation practices. Current code review datasets are scattered, vary widely in design, and provide limited insight into what review capabilities are actually being assessed. In this paper, we present a comprehensive survey of code review benchmarks spanning both the Pre-LLM and LLM eras (2015--2025). We analyze 99 research papers (58 Pre-LLM era and 41 LLM era) and extract key metadata, including datasets, evaluation metrics, data sources, and target tasks. Based on this analysis, we propose a multi-level taxonomy that organizes code review research into five domains and 18 fine-grained tasks. Our study reveals a clear shift toward end-to-end generative peer review, increasing multilingual coverage, and a decline in standalone change understanding tasks. We further identify limitations of current benchmarks and outline future directions, including broader task coverage, dynamic runtime evaluation, and taxonomy-guided fine-grained assessment. This survey provides a structured foundation for developing more realistic and comprehensive benchmarks for LLM-based code review.

cs.SE↗