Searcharxiv⌕ Search

arXiv subjects

Youcheng Sun

Publications and source records attributed to Youcheng Sun.

At least 19 recordsLinked to original sources
arXiv2026

Agentic Planning for Symbolic Execution

Symbolic execution seeks to explore feasible program paths, yet a practical run may exhaust its resources while much program behaviour remains unreached. We investigate a complementary way of extending its practical reach by reasoning about how the same tool is utilised from one bounded run to the next, while leaving ordinary state exploration to the underlying tool. We present Agolic, an agentic planning system that uses evidence from earlier runs to choose and configure later bounded symbolic execution (BSE) runs, which the underlying symbolic execution tool then carries out. The planning intelligence, available evidence and execution modes can be adapted to the symbolic execution tool and analysis objective. We evaluate one adaptation for branch-coverage exploration, in which an LLM-based agent reasons over source code, replayed coverage and earlier targeting attempts. We evaluate Agolic on several C and C++ programs. On every program, it extends the branch coverage obtained by continuous symbolic execution and covers more than $3\times$ as many branches on average. It also covers more branches than each individual corpus from coverage-guided fuzzing and compiler-based concolic execution in our evaluation and reaches branches absent from all comparison corpora combined on six of the seven programs. Taken together, these results point to considerable untapped potential in existing symbolic execution tools, some of which may be realised by reasoning about how their capabilities are used across runs while leaving state selection during ordinary symbolic exploration to the underlying tool.

cs.PL↗
arXiv2026

Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents

Reusable skills are becoming a standard interface for extending language agents with task procedures. Yet evaluators usually infer skill use from visible reasoning or the agent's own attribution. These signals show what the agent appears to use, not whether the skill changed its decision. We ask whether skill-augmented agents exhibit a \textbf{Reasoning Backroom}, a systematic gap between stated skill use and intervention-measured influence. We introduce BACKTRACE, an evaluation framework that pairs each skill-conditioned answer with a matched no-skill counterfactual, intervenes on skill meaning, wording, identity, content, and assignment, and elicits attribution only after the answer is committed. We instantiate the framework as BACKROOMBench, a verified testbed spanning controlled logic and competition mathematics, multiple skill conditions, single-agent and multi-agent settings, and diverse model families. Our evaluation reveals a pervasive provenance failure. Across models and domains, stated skill use often remains stable while causal reliance and signed utility vary, producing both silent uptake and performative use. Behavioral effects follow procedural content more reliably than displayed skill identity, whereas stated attributions respond strongly to artifact availability. Observational detectors based on direct skill-use claims, text mentions, trace similarity, and an LLM judge do not identify which decisions actually depend on the skill. In multi-agent systems, skill influence can survive communication even after its source is lost, while no-skill teams still name skills and sources that were never supplied. These findings establish the Reasoning Backroom as a general AI provenance problem whose audit requires intervention.

cs.AI↗
arXiv2026

SuperPass: Fast-Tracking Blocking Threads to Mitigate Priority Inversion on Mobile Devices

Priority inversion occurs when a high-priority thread is delayed by a lower-priority one. Although well studied in real-time systems, its impact in general-purpose OSes (e.g., Android) remains underexplored. On Android, we find that priority inversions happen frequently and can delay latency-critical threads, degrading user experience. For example, the foreground app's UI thread is frequently blocked by low-priority threads, with blocking durations of up to 210 ms, enough to cause dropped frames. Existing solutions designed for real-time systems fail to eliminate long priority-inversion blockings on latency-critical threads and may introduce high overhead on Android. To solve this problem, we uncover two insights on Android: 1) long blockings are mainly due to the accumulated CPU waiting time of low-priority blocking threads rather than their critical-section latency; and 2) although latency-critical threads can be blocked by many concurrent readers, tracking a limited number of them is sufficient to achieve good responsiveness with low overhead in most cases. Guided by these insights, we propose SuperPass, a lightweight kernel mechanism that mitigates priority inversion by fast-track scheduling of low-priority threads blocking latency-critical threads. It introduces a scheduler fast track that grants immediate CPU access to threads blocking latency-critical threads, and employs a lock-level detector that effectively identifies most such blocking threads. We evaluate SuperPass on a Google Pixel 8 smartphone. Taking UI thread as a case study, SuperPass decreases the 99.9th-percentile blocking duration by 72.0% and blocking count by 47.7% on average compared to the default scheduler, and reduces janky frames by 29.2% with a system-wide CPU overhead of only 0.74%. SuperPass also outperforms existing approaches including priority inheritance, real-time UI promotion, and Proxy Execution.

cs.OS↗
arXiv2026

Partial Contracts Suffice: Sound, LLM-Inferred Regression Verification

Software evolves continuously, yet ensuring that a patch preserves intended behavior without re-verifying an entire codebase remains difficult. Regression verification addresses this problem, but existing techniques require expensive whole-program reasoning or rely on manually written specifications that are rarely available in practice. We present the first contract-based regression verification tool. Contract soundness is ensured by proving all function versions match the behavior. The contract then verifies program flow via assume-guarantee. We ask whether a partial, caller-sufficient contract, rather than a full behavioral specification, is enough. On Frama-C-Problems we strengthen each inferred contract past what the caller needs and measure how much tighter it becomes. It barely moves: for most targets in every model the caller-sufficient contract is already the tightest the loop reaches, and our tightness comparator rates the partial and strengthened contracts equivalent for the large majority of targets it can compare. Partial-spec contracts thus capture nearly all the attainable tightness, so stopping at caller-sufficiency costs almost nothing. The regression check underneath is sound: on the third-party EqBench-C suite it never fabricates an equivalence, returning zero false proofs and reporting an unprovable difference instead. It also surfaced nine pairs that EqBench mislabels as equivalent, more than a concurrent tool reports. The contracts themselves are inferred automatically from the checker's own counterexamples, with no separate specification step; on Frama-C-Problems and the ANSSI X509 parser this reaches a verification rate comparable to tools AutoSpec and Preguss, while a passing result certifies at least as strong a property, which we call \emph{safety-preserving conditional equivalence}: enforcement plus caller-sufficiency.

cs.SE↗
arXiv2026

SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

Large Language Model (LLM)-based agents increasingly automate software engineering tasks through reusable skills, natural-language instruction documents that guide planning and execution. Open skill marketplaces enable users to assemble agents by co-activating community-contributed skills, but marketplace operators typically audit skills in isolation. As a result, individually benign skills may interact to redirect an agent toward unintended objectives, which we term implicit intents. Detecting such intents is challenging because the effect emerges only through skill composition, execution environments are often unavailable at admission time, and the space of possible co-activations grows exponentially with marketplace size. In this paper, we formulate implicit-intent discovery as a fuzzing problem over skill compositions, where skill compositions are the unit under test, planning artifacts expose agent intent before execution, and deviations from a skill-free baseline serve as a differential oracle. Based on this formulation, we propose skillfuzz, the first execution-free testing approach that extracts structured skill contracts and uses contract-guided Monte Carlo Tree Search to prioritize potentially conflicting compositions. Across representative skill-marketplace workloads, skillfuzz discovers over 1,000 distinct implicit intents under a fixed query budget, confirms more than 80% of the highest-risk flagged compositions during execution-time validation, and identifies substantially more high-severity implicit intents than alternative search strategies while exploring only a fraction of the pairwise interaction space they require.

cs.SE↗
arXiv2026

Skill Coverage: A Test Adequacy Metric for Agent Skills

Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance. However, a task outcome does not reveal which parts of a reusable skill were exercised, nor whether the agent followed the relevant skill instructions when those parts were exercised. This gap makes it unclear whether a skill has been adequately tested, or whether observed task failures provide actionable evidence for improving agent skill effectiveness. To fill this gap, we introduce skill coverage, a trajectory-based test-adequacy metric for reusable agent skills. Our framework extracts skill behavior constraints from each skill, translating natural-language skill instructions into semi-structured constraints that specify the expected agent behavior under particular conditions. It then determines whether each constraint is covered by an agent trajectory and, for covered constraints, assigns a Pass or Fail verdict according to the agent behavior. We apply this framework to SkillsBench. The results show that agent trajectories on the benchmark leaderboard cover only 38.66 to 45.51% of the extracted skill behavior constraints on average. We then use Fail verdicts to strengthen the corresponding skill content only by emphasizing the original instructions that the agent failed to follow, and run the same tasks with the strengthened skills. This emphasis yields an average 16.0% recovery rate of the failed tasks across the five agent-model rows. These results show that skill coverage is both a test-adequacy metric and a fine-grained signal for observing skill-use behavior. In failed tasks, failed constraint labels provide actionable evidence for improving agent skill effectiveness. A project website accompanies the paper.

cs.AI↗
arXiv2026

Agentic Model Checking

Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a paradigm that couples LLM agents with a bounded model checking backend under the principle agents propose, solvers verify: agents handle tasks requiring semantic judgment (spec inference, check selection, counterexample classification, refinement proposal) while BMC discharges every soundness-relevant decision. The paradigm rests on three commitments. Specifications are inferred top-down from caller context in a restricted DSL that translates deterministically into the backend's assume/assert primitives, with optional functional-correctness clauses lifting verification from panic-freeness to behavioural faithfulness. Verification is compositional: each function is checked in isolation against its spec with callees replaced by postcondition-constrained stubs, so per-query cost scales with a single function's state space and refinements propagate automatically to callers. Counterexamples are not bug reports: they pass through a validation pipeline (reachability, callee feasibility, dynamic replay, realism audit) that distinguishes active in-tree crashes from latent public-API failures, while modelling artifacts drive a refinement loop rather than being suppressed. We instantiate the approach in BMC-Agent and evaluate it on LLM-generated kernel and compiler code in C and Rust alongside mature OSS-Fuzz-hardened libraries, confirming real defects, producing bounded clean verifications on heavily-fuzzed surfaces, and establishing functional equivalence on selected algorithmic functions.

cs.SE↗
arXiv2026

Responsible Agentic AI Requires Explicit Provenance

Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, despite being widely discussed, remains a subjective and unenforced concept, as no current agentic framework produces the quantifiable, traceable, and interventionable provenance needed to assign it when harm emerges from compositions no single party designed. We position that what is missing is not better benchmark-level evaluation but $\textbf{explicit provenance}$ across the full agentic lifecycle, which is the only viable basis for making responsibility computable and actionable. We advance this agenda along four axes: establishing $\textit{why}$ such provenance is a structural necessity by identifying responsibility gaps across sociotechnical dimensions, formalizing $\textit{what}$ it must encode through a causal attribution function and responsibility tensor, discussing $\textit{how}$ it can be made computable across four lifecycle layers with preliminary experiments showing that provenance is estimable and interveneable online before irreversible harm accumulates, and examining $\textit{who}$ bears responsibility through a concrete agentic incident. Explicit provenance is not a discretionary refinement but the necessary condition for responsible agentic AI, and no stakeholder across its ecosystem can afford to treat it as optional.

cs.AI↗
arXiv2026

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

cs.SE↗
arXiv2026

Compartmentalization-Aware Automated Program Repair

Software compartmentalization breaks down an application into compartments isolated from each other: an attacker taking over a compartment will be confined to it, limiting the damage they can cause to the rest of the application. Despite the security promises of this approach, recent studies have shown that most existing compartmentalized software is plagued by vulnerabilities at cross-compartment interfaces, allowing an attacker taking over a compartment to escape its confinement and negate the security guarantees expected from compartmentalization. In that context, securing cross-compartment interfaces is notoriously difficult and engineering-intensive. In light of recent advances in Automated Program Repair (APR), notably through the use of Large Language Models (LLMs), this paper presents a work in progress investigating the suitability of LLM-based APR at securing cross-compartment interfaces as automatically as possible. We observe that existing APR approaches and general purpose/code-centric LLMs used as is are unfit for this task, and present the design, implementation, and early results of a new APR framework dedicated to compartment interface safety. The framework integrates into a feedback loop 1) a specialized fuzzer uncovering cross-compartment interface vulnerabilities; 2) a patch generation component bridging the lack of compartmentalization awareness of existing LLMs with a series of analysis techniques; and 3) a patch validation component assessing the effectiveness of generated vulnerability fixes. We validate our framework over a sample interface vulnerability, comparing it to a naive use of general-purpose LLMs, and discuss future research avenues.

cs.CR↗
arXiv2026

ClawMobile: Rethinking Smartphone-Native Agentic Systems

Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented control interfaces, and rapidly changing application states. As large language models (LLMs) evolve from conversational assistants to action-oriented agents, achieving reliable smartphone-native autonomy requires rethinking how reasoning and control are composed. We introduce ClawMobile as a concrete exploration of this design space. ClawMobile adopts a hierarchical architecture that separates high-level language reasoning from structured, deterministic control pathways, improving execution stability and reproducibility on real devices. Using ClawMobile as a case study, we distill the design principles for mobile LLM runtimes and identify key challenges in efficiency, adaptability, and stability. We argue that building robust smartphone-native agentic systems demands principled coordination between probabilistic planning and deterministic system interfaces. The implementation is open-sourced~\footnote{https://github.com/ClawMobile/ClawMobile} to facilitate future exploration.

cs.MA↗
arXiv2026

VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection

Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration (CWE) categories. We propose VulReaD, a knowledge-graph-guided approach for vulnerability reasoning and detection that moves beyond binary classification toward CWE-level reasoning. VulReaD leverages a security knowledge graph (KG) as a semantic backbone and uses a strong teacher LLM to generate CWE-consistent contrastive reasoning supervision, enabling student model training without manual annotations. Students are fine-tuned with Odds Ratio Preference Optimization (ORPO) to encourage taxonomy-aligned reasoning while suppressing unsupported explanations. Across three real-world datasets, VulReaD improves binary F1 by 8-10% and multi-class classification by 30% Macro-F1 and 18% Micro-F1 compared to state-of-the-art baselines. Results show that LLMs outperform deep learning baselines in binary detection and that KG-guided reasoning enhances CWE coverage and interpretability.

cs.SE↗
arXiv2026

Specification Vibing for Automated Program Repair

Large language model (LLM)-driven automated program repair (APR) has advanced rapidly, but most methods remain code-centric: they directly rewrite source code and thereby risk hallucinated, behaviorally inconsistent fixes. This limitation suggests the need for an alternative repair paradigm that relies on a representation more accessible to LLMs than raw code, enabling more accurate understanding, analysis, and alignment during repair. To address this gap, we propose VibeRepair, a specification-centric APR technique that treats repair as behavior-specification repair rather than ad-hoc code editing. VibeRepair first translates buggy code into a structured behavior specification that captures the program's intended runtime behavior, then infers and repairs specification misalignments, and finally synthesizes code strictly guided by the corrected behavior specification. An on-demand reasoning component enriches hard cases with program analysis and historical bug-fix evidence while controlling cost. Across Defects4J and real-world benchmarks and multiple LLMs, VibeRepair demonstrates consistently strong repair effectiveness with a significantly smaller patch space. On Defects4J v1.2, VibeRepair correctly repairs 174 bugs, exceeding the strongest state-of-the-art baseline by 28 bugs, which corresponds to a 19% improvement. On Defects4J v2.0, it repairs 178 bugs, outperforming prior approaches by 33 bugs, representing a 23% improvement. Evaluations on real-world benchmarks collected after the training period of selected LLMs further confirm its effectiveness and generalizability. By centering repair on explicit behavioral intent, VibeRepair reframes APR for the era of "vibe" coding: make the behavior sing, and the code will follow.

cs.SE↗
arXiv2026

SWE-Manager: Selecting and Synthesizing Golden Proposals Before Coding

Large language model (LLM) research in software engineering has largely focused on tasks such as code generation and bug repair. In practice, teams often draft multiple candidate proposals for fixing an issue and then deliberate on one golden proposal for implementation. This selection requires not only assessing the issue's scope, impact, and urgency, but also a clear understanding of each proposal's strengths and weaknesses. A good selection could make issue resolution more reliable while reducing regression and operational risk, whereas a poor choice can increase risk and even cause unpredictable failures. We first conduct a manual study of real-world issues to characterize the rationales maintainers use when selecting among competing proposals. Motivated by these findings, we introduce SWE-Manager, a joint selection and synthesis approach that selects the best proposal and synthesizes a golden proposal. SWE-Manager is an 8B model trained via reinforcement learning (RL) to compare proposals, justify its choice, and synthesize a golden proposal for implementation. We view proposal selection as a reasoning task, mirroring how technical managers review competing proposals by weighing issue context and each proposal's solution without executing code or running tests. On the SWE-Lancer Manager benchmark, SWE-Manager achieves 53.21 selection accuracy and 57.75 earn rate, earning 152,750 dollars and outperforming strong baselines including GPT-5. To further evaluate the effectiveness of SWE-Manager in real-world issue resolution, we design the P2A framework, which simulates a real-world workflow where multiple proposals are drafted, reviewed, and a golden proposal is selected for implementation ...

cs.SE↗
arXiv2026

Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks

Private macOS frameworks underpin critical services and daemons but remain undocumented and distributed only as stripped binaries, complicating security analysis. We present MOTIF, an agentic framework that integrates tool-augmented analysis with a finetuned large language model specialized for Objective-C type inference. The agent manages runtime metadata extraction, binary inspection, and constraint checking, while the model generates candidate method signatures that are validated and refined into compilable headers. On MOTIF-Bench, a benchmark built from public frameworks with groundtruth headers, MOTIF improves signature recovery from 15% to 86% compared to baseline static analysis tooling, with consistent gains in tool-use correctness and inference stability. Case studies on private frameworks show that reconstructed headers compile, link, and facilitate downstream security research and vulnerability studies. By transforming opaque binaries into analyzable interfaces, MOTIF establishes a scalable foundation for systematic auditing of macOS internals.

cs.CR↗
arXiv2026

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an unexpected attack surface. This paper introduces a novel threat where colluding agents steer victim beliefs using only truthful evidence fragments distributed through public channels, without relying on covert communications, backdoors, or falsified documents. By exploiting LLMs' overthinking tendency, we formalize the first cognitive collusion attack and propose Generative Montage: a Writer-Editor-Director framework that constructs deceptive narratives through adversarial debate and coordinated posting of evidence fragments, causing victims to internalize and propagate fabricated conclusions. To study this risk, we develop CoPHEME, a dataset derived from real-world rumor events, and simulate attacks across diverse LLM families. Our results show pervasive vulnerability across 14 LLM families: attack success rates reach 74.4% for proprietary models and 70.6% for open-weights models. Counterintuitively, stronger reasoning capabilities increase susceptibility, with reasoning-specialized models showing higher attack success than base models or prompts. Furthermore, these false beliefs then cascade to downstream judges, achieving over 60% deception rates, highlighting a socio-technical vulnerability in how LLM-based agents interact with dynamic information environments. Our implementation and data are available at: https://github.com/CharlesJW222/Lying_with_Truth/tree/main.

cs.CL↗
arXiv2025

The 4/$\delta$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee

The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows. However, current methods remain unreliable: without a solid theoretical footing, the refinement process acts as a black box that may oscillate, loop, or diverge. This work bridges this critical gap by developing an LLM-Verifier Convergence Theorem, providing the first formal framework with provable guarantees for termination in multi-stage verification pipelines. We model the interaction not as a generic loop, but as a sequential absorbing Markov Chain comprising four essential engineering stages: \texttt{CodeGen}, \texttt{Compilation}, \texttt{InvariantSynth}, and \texttt{SMTSolving}. We prove that for any non-zero stage success probability ($\delta > 0$), the system reaches the \texttt{Verified} state almost surely. Furthermore, because of the sequential nature of the pipeline, we derive a precise latency bound of $\mathbb{E}[n] \leq 4/\delta$. We stress-tested this prediction in an extensive empirical campaign comprising over 90,000 trials. The results match the theory with striking consistency: every run reached verification, and the empirical convergence factor clustered tightly around $C_f\approx 1.0$, confirming that the $4/\delta$ bound accurately mirrors system behavior rather than serving as a loose buffer. Based on this data, we identify three distinct operating zones -- marginal, practical, and high-performance -- and propose a dynamic calibration strategy to handle parameter drift in real-world environments. Together, these contributions replace heuristic guesswork with a rigorous architectural foundation, enabling predictable resource planning and performance budgeting for safety-critical software.

cs.AI↗
arXiv2025

LLM-Driven Kernel Evolution: Automating Driver Updates in Linux

Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel.

cs.SE↗