Searcharxiv⌕ Search

arXiv subjects

Jing Shao

Publications and source records attributed to Jing Shao.

At least 19 recordsLinked to original sources
arXiv2026

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is critical in Chinese harmful-content evaluation, where linguistic variation and adversarial transformations can obscure risky intent. We introduce C-SafeQA, a policy-grounded benchmark for response-level Chinese safety evaluation. It comprises 538 base queries and 8,877 adversarial queries answered by four full-model LLM deployments, yielding 37,660 query-response records labeled safe, unsafe, or disputed. Reference labels are generated through agreement-aware multi-model adjudication and blind audits of stratified subsets by three safety experts. C-SafeQA supports both evaluation of target-model safety and auditing of seven automated safety judges against shared reference labels. Unsafe-response rates range from 0.93% to 3.35% on base queries and from 11.68% to 30.05% on adversarial queries. On the adversarial subset, judges show substantial trade-offs between unsafe-response recall and risk-query-conditioned safe-response false positive rate, and no judge dominates all metrics. Both acrostic transformations reduce unsafe recall for all seven judges, revealing mechanism-specific evaluator weaknesses. Dataset records, metadata, verification code, and judge scripts are publicly released to support recomputation, while benchmark construction, target-response generation, and private adjudication remain outside the release boundary.

cs.CR↗
arXiv2026

Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off. On repeated GLM-5 runs, SkillSonar reduces ID ASR from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115. Further analyses demonstrate transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers. Ablations further show that explicit safety responsibility assignment and the skill-native representation are both important to the observed gains.

cs.CR↗
arXiv2026

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage, and unauthorized actions. Existing guardrails often evaluate completed trajectories, leaving pre-execution monitoring of step-level actions underexplored. We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed. To train StepGuard, we introduce StepGen, an automatic data engine that generates safe and unsafe trajectories with the same context but different actions at the risky step. To further reduce over-defense and under-defense, we propose Balance-GRPO, which dynamically balances learning between safe and unsafe actions based on their observed accuracy. Experiments show that StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4. When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3% relative to the no-guard setting, while mean utility drops by only 2.8 percentage points.

cs.AI↗
arXiv2026

MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps

LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental content, they are highly vulnerable to environmental injection attacks, which include indirect prompt injections and adversarial instructions. Such attacks can manipulate the behavior of agents without user awareness through diverse channels encountered in everyday mobile use. Despite these risks, existing benchmarks often fail to capture everyday user scenarios, lacking a systematic evaluation of GUI agents under environmental injection attacks on mobile devices. To address this gap, we introduce MobileWorldSafety, a benchmark of 142 risk tasks built on real Android applications. For each task, we define a programmatically verifiable risk indicator over the final system state and evaluate outcomes with a two-stage pipeline: rule-based verification handles unambiguous cases, while an LLM judge adjudicates ambiguous ones. This distinguishes safety failures from capability failures and enables objective and reproducible assessment. Evaluations on six agents, including both general agents and specialized GUI agents, demonstrate that all agents remain highly vulnerable, with attack success rates ranging from 40.4% to 66.9%. These findings indicate that current agents often fail to maintain safety alignment when adversarial content is presented as ordinary mobile context. MobileWorldSafety provides a foundation for quantifying these vulnerabilities and advancing research on robust mobile GUI agents.

cs.CR↗
arXiv2026

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control. Existing safety mechanisms often treat the harness as a fixed deployment artifact, limiting their ability to evolve with emerging risks. Moreover, coupled functions across harness components obscure safety responsibility attribution, making localized evolution difficult. We propose Safety Harness Evolution (SHE), a framework that learns evolving safe boundaries from rollout trajectories. SHE decomposes the harness into four artifacts with explicit safety responsibilities, including the System Prompt, Rule Bank, Safety Memory, and Tool Policy, defining clear functional boundaries for localized evolution. Based on this decomposition, SHE introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through safety-utility validation. Experiments on Agent-SafetyBench demonstrate that SHE effectively enhances safety through harness evolution, achieving a 3.1x ASR reduction compared with static SafeHarness, while also improving benign utility. The evolved harness further generalizes to unseen risks on the held-out AgentHarm benchmark and transfers across agent models without additional evolution.

cs.AI↗
arXiv2026

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such settings, hallucinations are particularly damaging: a single erroneous claim on a foundational concept can propagate through multi-step reasoning and corrupt entire trajectories. Existing hallucination benchmarks largely operate at the surface level, treating facts in isolation and relying on uniform accuracy metrics that ignore this topological structure. We address this gap with SCHEMA, the first evidence-grounded, topology-aware evaluation framework for hallucinations in scientific agents. SCHEMA automatically constructs scientific concept graphs from benchmark seeds and literature evidence, synthesizes graph-grounded tasks spanning claim verification, multi-hop reasoning, open-ended explanation, and experimental code generation, and evaluates agents with two complementary diagnostics. A trajectory hallucination pipeline audits intermediate reasoning at scale via a topology-weighted severity score, while a multi-agent counterfactual attribution module pinpoints the causal mechanism behind selected failures. SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning. These results indicate that for high-stakes scientific applications, terminal accuracy alone is an insufficient signal of agent reliability, motivating mechanism-level evaluation grounded in knowledge topology. Code is available at https://github.com/circles-post/SCHEMA.

cs.AI↗
arXiv2026

Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions

Deep Research agents conduct long-horizon investigations by iteratively planning, retrieving evidence, and generating reports. However, it remains unclear whether they can resist apparently credible but factually false information introduced into these workflows. To study this failure mode, we introduce MisKnow-Agent, a controlled evaluation framework that constructs task-specific documents supporting manually audited false conclusions with controlled authority cues and source styles. Applied to the tasks from DeepResearch Bench, it generates 5,933 misleading documents after filtering. We evaluate DeerFlow and WebThinker with three backbone LLMs, together with Gemini Deep Research, using a report-level false-conclusion adoption rate (FCAR) that counts only reports endorsing the false conclusion. Across the configurations, introducing one misleading document increases the mean FCAR from 0\% in the no-injection control to 54.7\%. FCAR varies substantially with lifecycle stage and framework design, and also with source authority and presentation style, whereas search-result rank and additional documents beyond the first have limited influence. Although cross-model verification consistently classifies retained instances as misleading, Deep Research agents can still adopt the corresponding false conclusions during long-horizon research. Pre- and post-research defenses reduce FCAR but do not eliminate adoption, motivating continuous verification when evidence enters intermediate research states and final synthesis. To facilitate reproducibility, our code and dataset are publicly available at https://github.com/whfeLingYu/MisKnow-Agent and https://huggingface.co/datasets/whfeLingYu/Misleading_Knowledge, respectively.

cs.AI↗
arXiv2026

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding. To address this, we introduce SciHazard, a real-world-grounded benchmark for scientific risks and a dataset agnostic evaluation framework for measuring harmfulness. SciHazard contains 2400 hazardous questions and 600 oversafety questions across 12 disciplines, with both queries grounded in regulated entities and documented failure scenarios. To compute \textsc{DeHarm-Score} , we develop a decomposed evaluating procedure that combines query hazard severity, refusal behavior, and response-level risk. For non-refused responses, it further decomposes response-level harm into \textsc{Executability}, quantified via dynamic checklists with importance weighting, and \textsc{Net-new risk}, assessed through retrieval-augmented claim extraction and synthesis-barrier verification. An expert-validation study shows that \textsc{DeHarm-Score} improves agreement with expert annotations by 90.17\% over the strongest baseline. We benchmark 31 frontier LLMs and deep research agents in an extensive scientific safety evaluation. Notably, deep research agents yield 32.3\% higher mean \textsc{DeHarm-Score} than standard LLMs, exposing autonomous agents as a critical blind spot in current safety defenses. Code and dataset are available at https://anonymous.4open.science/r/DeharmScore-7B55.

cs.AI↗
arXiv2026

An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models: (i) Intern-BioBreaker outperforms baseline attack models and reveals widespread bio-risk jailbreak vulnerabilities across both open-weight and proprietary frontier LLMs, with several targets reaching near-saturated or 100% task-level attack success rate (ASR); (ii) in sequence-level case studies, GPT-5.5 can be induced to generate modified viral candidate sequences with pathogenic potential; the corresponding translated proteins may exhibit even stronger receptor-binding affinity and thus enhanced infection potential; and (iii) end-to-end verification shows that selected model-generated biological designs are not merely textual artifacts, but can be physically realized under controlled experimental settings. These findings underscore the need for stronger biological red-teaming, nucleic acid synthesis screening, and safety mechanisms that keep pace with model capabilities.

cs.CL↗
arXiv2026

Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment

Large language model (LLM)-based Socratic tutors increasingly guide students through multi-turn questioning, but they can suffer from scaffolding collapse: under sustained student pressure, a tutor gradually abandons guided inquiry and reveals solutions directly. Prior defenses primarily constrain observable responses through prompting, preference optimization, or filtering, leaving the internal representation drift that precedes trajectory-level collapse largely unaddressed. We propose Scaffold-Preserving Representation Alignment, a two-stage framework that first warms up a Socratic tutor with supervised fine-tuning, then combines trajectory-weighted direct preference optimization with a margin-preserving representation loss anchored to frozen reference states. Our method is designed to maintain separation between scaffold-preserving and collapse-inducing hidden states across dialogue turns. We evaluate our method across five STEM disciplines and five red-teaming attack strategies. On Qwen3-8B, our method lowers Collapse Rate to 32%, delays average collapse onset beyond nine turns, and keeps over-refusal low, suggesting that representation-level alignment can improve the robustness of long-horizon Socratic tutoring under our red-teaming protocol.

cs.AI↗
arXiv2026

READER: Dynamic LLM Provenance from Query-Varying Interactions

Existing black-box LLM provenance methods achieve comparability by querying every candidate model with the same diagnostic prompts. In deployment, auditors inherit a different evidence stream: heterogeneous prompt-response traces that arrive incrementally. We formalize dynamic black-box LLM provenance: after enrolling a fixed candidate ecosystem, attribute query-varying interactions at any available evidence budget. READER recovers comparability through a frozen proxy LLM. It projects proxy states aligned with response tokens onto length-normalized DC and first-AC modes, capturing response-wide activation location and coarse trajectory evolution. An enrollment-trained linear probe converts each fingerprint into source evidence, and Bayesian accumulation reuses this evidence unit from one observation to many. We introduce Agent500, containing 50,000 responses from 100 local and API sources to 500 heterogeneous agent prompts. On 100-way attribution, READER reaches $50.4\%$ accuracy from one response and $96.2\%$ from 100, compared with $33.0\%$ and $79.0\%$ for the strongest dynamic baselines. Four distinct proxy families all exceed $94.8\%$ at the latter budget. Controlled response-length and Math100 domain shifts expose the limits of zero-retraining transfer. Component analysis reveals a task-dependent spectral division of labor: DC dominates dynamic source identity, while first AC dominates static relationship evidence. Their joint fingerprint provides a shared measurement space for both tasks. READER audits observed text without target internals or audit-only queries. Code and data are available at https://github.com/LeoJeshua/READER.

cs.AI↗
arXiv2026

Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning

Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions. Existing approaches mainly improve these behaviors through inference-time correction or coarse-grained reward signals based on decision outcomes and structured checklists, leaving the uncertainty characteristics of agent decisions underexplored. We observe that decision-oriented reinforcement learning tends to weaken the uncertainty separation between correct and incorrect actions, resulting in overconfident mistakes and weaker exploration signals. Therefore, we propose TRUST, which incorporates uncertainty quantification into reward design as a repulsive force for maintaining uncertainty separation, and labels lightweight key-turn annotations for unified post-training of multi-turn trajectories. Experimental results across diverse tool-use benchmarks show that TRUST consistently enhances both decision quality and agent performance while maintaining more reliable uncertainty estimates during optimization.

cs.AI↗
arXiv2026

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building such person-grounded agents remains difficult because actionable knowledge associated with a person or role is usually embedded in heterogeneous traces rather than written as clean instructions. Existing memory and persona systems capture fragments of this evidence, while skill frameworks provide portable packaging formats; however, there is no end-to-end workflow for distilling these traces into inspectable, correctable, and agent-usable skills. We present an automated trace-to-skill distillation system for generating person-grounded AI skills via expert knowledge distillation. Given materials from a target person or role, COLLEAGUE.SKILL produces a versioned skill package with two coordinated tracks: a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. The package can be inspected, invoked, updated through natural-language feedback, rolled back, installed across agent hosts, and optionally prepared for controlled distribution. We describe the artifact contract, generation workflow, correction lifecycle, deployment surface, and domain presets implemented in the open-source system. At the time of writing, the public repository has approximately 18.5k GitHub stars; the gallery lists 215 skills from 165 contributors and more than 100k cumulative stars across listed skill cards. The system illustrates how person-grounded skills can be represented as portable, correctable packages rather than opaque prompts or hidden memories.

cs.AI↗
arXiv2026

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex and OpenClaw execution scenarios. We further build a taxonomy-guided data engine with influence-function purification to train lightweight AgentDoG 1.5 variants (0.8B, 2B, 4B, and 8B parameters) using only around 1k samples, achieving comparable performance with leading closed-source models (e.g., GPT-5.4). Based on AgentDoG 1.5, we construct a highly efficient agentic safety SFT and RL training environment, which reduces deployment overhead in Docker-level environments by two orders of magnitude. Finally, we deploy AgentDoG 1.5 as a training-free online guardrail for real-time safety moderation. Extensive experimental results indicate that AgentDoG 1.5 achieves state-of-the-art performance in diverse and complex interactive agentic scenarios. All models and datasets are openly released.

cs.AI↗
arXiv2026

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education

Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social trajectories are irreversibly shaped, while real-world trials are slow, ethically constrained, and institutionally locked. LLM-based educational simulators have emerged as a potential remedy, but many still collapse learning into persona-conditioned role-play and, when optimized only to reproduce existing classrooms, can structurally penalize the institutional novelty that pedagogical reform requires. In this work, we introduce AgentSchool, an LLM-driven multi-agent simulator that models learning as state transition rather than prompted behavior. AgentSchool couples cognitively growable student agents -- equipped with weighted subject knowledge graphs, thinking-workflow pools, and explicit misconceptions -- with adaptive teacher agents that plan, scaffold, and reflect along the Zone of Proximal Development, embedded in a configurable scenery generator that situates instruction within both formal and informal learning fields, and a multi-scale simulator that decouples interaction scale, temporal granularity, and simulation duration. Experiments show that structured student agents produce more differentiated mastery and misconception traces than a baseline simulator, while teacher-agent comparisons show backbone-dependent patterns consistent with ZPD-informed adaptation. Further, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom social theories. Beyond its role as an educational research instrument, AgentSchool frames education as a socially meaningful testbed for long-horizon memory, multi-agent coordination, and future institutional reasoning under organizational pressure.

cs.AI↗
arXiv2026

UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities

Agent benchmarks are increasingly used to compare large language models (LLMs) across domains, yet a reported score reflects a complete model--harness--environment configuration rather than the model alone. Benchmark packages couple native tasks with specific prompts, tool protocols, orchestration logic, and sometimes dynamic external resources, making cross-benchmark comparisons sensitive to implementation and resource conditions. We present UniACE, a unified framework for model-centric evaluation under an explicit, common execution condition. UniACE represents each benchmark as an instruction--tool--environment triplet, executes LLMs through a shared, task-agnostic harness in isolated per-task runtimes, and preserves native success criteria. For tasks that rely on dynamic resources, an optional offline mode replaces live access with fixed, pre-collected snapshots. Its evaluation protocol further standardizes efficiency measurement, execution records, and trace-based failure attribution. We migrate 7 benchmarks spanning 24 domains and evaluate 15 models in more than 400K rollouts consuming 5B tokens. Comparisons with source implementations show large bidirectional score changes and model-ranking reversals, while matched online and offline runs reveal substantial sensitivity to accessible evidence and its representation. Under the shared UniACE configuration, efficiency and failure profiles expose task-dependent model behaviors hidden by task-success scores alone. These findings motivate reporting agent benchmark outcomes as properties of an explicit evaluation configuration, enabling more interpretable and reproducible cross-benchmark comparisons. Codes and benchmarks at are available at https://github.com/whfeLingYu/A-Unified-Framework-for-the-Evaluation-of-LLM-Agentic-Capabilities, https://huggingface.co/datasets/whfeLingYu/Unified_Agent_Framework.

cs.AI↗
arXiv2026

PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning

As LLMs continue to scale up, improving training efficiency heavily relies on effective data utilization. Data selection mitigates this issue by allocating the limited training budget to high-value examples that optimally facilitate the model's target behavior. Most existing approaches define target behavior via a set of target examples and score candidate training data based on their estimated influence on these samples. However, such methods uniformly treat all target examples as equally important, ignoring the varying relevance of individual examples to model optimization. Specifically, target examples that align closely with the model's inherent behavior deliver stronger supervisory signals, whereas discrepant examples yield only weak and ineffective local guidance. We propose PRISM, a Preference-aware Influence function based Data Selection Method. It leverages model preference to assign weights to target examples and builds a preference-aware target direction. PRISM evaluates candidate training samples according to their influence on this direction, and prioritizes data budget allocation to samples that effectively drive the model to match expected target behavior. Theoretical analysis verifies that weighted preference construction generates a superior first-order gradient direction for boosting target preference, compared with uniform aggregation strategies. Extensive experiments covering diverse model architectures and parameter scales demonstrate that PRISM achieves better performance in efficient fine-tuning and safety-aligned supervised fine-tuning rectification. The results validate that accurate characterization of target behavior serves as the core of cost-effective data selection.

cs.LG↗
arXiv2026

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models, such that perturbations align with transferable semantic cues rather than surrogate-specific behaviors. However, existing methods suffer from spatial-domain feature redundancy and surrogate-specific gradient signals, thereby hindering cross-model transferability. In this paper, we propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective. For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus. For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a \textit{model-agnostic} low-pass regularizer that modulates the surrogate gradient using only the geometric frequency coordinate, \textit{i.e.}, no surrogate-derived statistic is involved, so that FGR is model-agnostic by construction, removing surrogate-specific high-frequency artifacts while preserving transferable low-frequency directions. Together, the two components form a unified frequency-domain treatment of transferability. Extensive experiments on $15$ flagship MLLMs across $7$ vendors show that FRA-Attack achieves superior cross-model transferability, particularly with state-of-the-art performance on GPT-5.4, Claude-Opus-4.6 and Gemini-3-flash.

cs.CR↗