Artificial Intelligence · Cross-listed from cs.RO
Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots
S. M . Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, W. K. R. Sachinthana et al. (+1 more)
Vision-
Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-
language commands into executable actions grounded in visual scene understanding. This tight coupling between perception and instruction-following introduces a new attack surface:
adversarial text placed within the
robot's visual field can act as an indirect
prompt injection into the VLM's
reasoning stack. We present a systematic study of physical
prompt injection attacks against VLM-controlled sorting, introducing a four-category taxonomy, indirect signage, task redefinition, authority impersonation, and conflict injection, instantiated as a
benchmark of 20 attack
prompts evaluated across three physical scene layouts and three command formulations that vary in destination specificity and rule explicitness. Across 5,670 trials on three frontier VLMs (GPT-4o, Gemini 2.5 Flash, Qwen3-VL-32B), attacks succeed at 27.0%, 29.4%, and 5.0% respectively, with authority-impersonating and negation attacks transferring across all three models. Analysis of
reasoning traces reveals that successful compromise is nearly always conscious (99.9% acknowledgment rate), and that models defend through structurally different mechanisms, explicit rejection for Gemini, perceptual inattention for GPT-4o. We evaluate three simple mitigations:
prompt-based defense (75-100% effective, model-dependent), two-stage verification (85-100%), and pre-processing text masking (100%). Our findings show that VLM-controlled manipulation is meaningfully vulnerable to human-readable physical signage, and that simple defenses substantially reduce risk, though defense choice involves trade-offs. The defenses preserve general task capabilities in our
benchmark, but they may impair tasks that require reading in-scene labels.
Read the full abstract ▾
All authors S. M . Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, W. K. R. Sachinthana, Mohan Rajesh Elara
Artificial Intelligence
RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation
Shuhao Yan, Changhao He, Peng Hu et al. (+1 more)
Text-to-CAD generation translates natural-
language design intent into editable and executable parametric computer-aided design (CAD) codes, reducing the expertise and effort required for manual modeling. Existing methods incorporate fixed, externally supplied,
prompt-induced, or separately optimized critique mechanisms to optimize the generation process, but they do not necessarily optimize how feedback is interpreted and translated into effective corrective actions throughout the generation process. To bridge this feedback-utilization gap, we present RA-CAD (ReAct
Agent for CAD), a state-aware
agent that interacts with the CAD environment through a Generate–Execute–Critique–Rewrite loop. At each iteration, RA-CAD executes the current code and observes its outcome. Conditioned on the design instruction, current code, and execution feedback, the
agent then generates an explicit post-execution critique as an intermediate policy action. This critique either validates the current result for termination or provides revision-oriented guidance that conditions the next rewrite. CAD Code Bootstrapping (CCB) first establishes fundamental parametric CAD coding capabilities through supervised fine-tuning. Feedback-Driven
Agent Optimization (FAO) subsequently applies trajectory-level Group Relative Policy Optimization to both policy-generated code and critique sequences, assigning terminal F1 and Chamfer Distance rewards to the complete interaction trajectory. This formulation makes critique an outcome-aligned, learnable policy decision rather than an unoptimized auxiliary output. Experiments on CADFusion and Text2CAD show that RA-CAD achieves state-of-the-art execution validity and
geometric quality compared with existing methods and strong proprietary
language models, demonstrating the effectiveness of the proposed state-aware text-to-CAD
agent.
Read the full abstract ▾
All authors Shuhao Yan, Changhao He, Peng Hu, Xi Peng
Artificial Intelligence
Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing Objectives
Keziah Naggita
When an AI system is deployed, the individuals who use and or are evaluated by it form beliefs about how the system operates and use those beliefs to strategically present their preferences, behaviors, or attributes. The system then responds with feedback or a decision outcome, thereby creating a human-AI interaction loop. This thesis studies how to design and shape such interactions to achieve three goals: (1) help individuals develop accurate beliefs about the AI systems so they can improve and or secure favorable outcomes at minimal cost, (2) encourage improvement and or discourage gaming behaviors, and (3) ensure that the AI system continues to achieve its intended objectives, such as maximizing accuracy. To address these goals, the thesis is organized into three complementary parts that examine and study human-AI interactions from the perspectives of both evaluated individuals and AI systems. Together, the work presented in this thesis advances human-centered machine learning by providing principles and methods for designing AI systems that align with human needs, values, and capabilities. Methodologically, this thesis integrates theoretical analysis, data-driven modeling, human-subject experiments, and empirical evaluations on real-world and semi-synthetic
datasets.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
Victor Gialis, Maxime Metz, David Esteve et al. (+1 more)
Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spectral Aliasing Pretext (SAP), a self-supervised learning method that pretrains models on unlabeled vibration data by exploiting spectral aliasing. We deliberately undersample signals to create folded spectrum, then train a
Transformer to reconstruct the original unfolded spectrum. This pretext task forces the model to learn frequency-domain invariants characteristic of mechanical faults, without potentially destructive augmentations. Experiments on the CWRU
dataset show that SAP learns stable and highly discriminative representations. In a linear probing setting, SAP quickly achieves very high classification performance with only a small fraction of labeled data and low variance. In contrast, full fine-tuning, including fully supervised training, does not lead to more stable or better results. Overall, these findings suggest that SAP combined with linear probing can be more effective and reliable than fully supervised training for fault diagnosis with limited labeled data.
Read the full abstract ▾
All authors Victor Gialis, Maxime Metz, David Esteve, Abdenour Soualhi
Artificial Intelligence
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Wenhao Lin, Chenyu Yu, Xingwei Lin et al. (+6 more)
As large
language model (LLM)
agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services. Recent runtime guardrails mitigate such risks by checking proposed actions before execution, but many remain reactive: they primarily assess the apparent safety of the current action, lacking an explicit model of how risk evolves across the trajectory. This limitation creates a critical blind spot for long-horizon risks, where individually benign-looking actions can gradually drift the
agent toward hazardous states. In response, we propose DreamGuard, a proactive guardrail for LLM
agents built around a risk-aware world model. The world model maintains a compact recurrent latent state over the trajectory and predicts future latent states from which DreamGuard derives immediate-hazard and prefix-risk evidence. It then fuses these multi-horizon signals into intervention decisions before execution. Experiments across four
benchmarks and an online guardrail evaluation show that DreamGuard outperforms generic, reactive, and proactive guardrail baselines, achieves the best safety-utility trade-off among evaluated guardrails, and maintains an average end-to-end latency of 25 ms per call.
Read the full abstract ▾
All authors Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu
Artificial Intelligence · Cross-listed from cs.CL
Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models
Jewon Yeom, Jaewon Sok, Seonghyeon Park et al. (+3 more)
Masked
diffusion language models revise many masked output positions in parallel. We call a
token committed once it becomes visible and is never masked again, and call a response answer-first when the final answer commits before the
reasoning printed ahead of it. On 1,069 GSM8K test questions, an explicit step-by-step instruction increases the accuracy difference between unrestricted decoding and a decoder that permits commitment only near the left-most unresolved position; unrestricted decoding also produces more answer-first trajectories. On MATH-500, the two LLaDA models spend most of a short output canvas on
reasoning that commits after the answer, and the benefit of frontier gating decreases as that postanswer writing disappears. Dream-7B has little post-answer writing and follows a different accuracy pattern. A controlled four-option task reserves a one-
token answer position before generation. Delaying that position outperforms an equally timed
reasoning-
token delay on LLaDA-8B, LLaDA-1.5, and Dream-7B. The raw difference is largest on Dream, whose free accuracy on the controlled task is lower. Answers commit much earlier under the reserved-position interface than in ordinary free-form generation, which limits how far the intervention result can be generalized. Commitment order affects the context used to complete a response and the allocation of a finite output canvas.
Read the full abstract ▾
All authors Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Hwiyeong Lee, Taesup Kim
Artificial Intelligence
Grounded Well-Condition Anomaly Detection on the Volve Field: Constructed Labels, a Baseline, and a Dual-Head Model
Gospel Bassey, Samuel Bassey and Vincent Fakiyesi
Most public
benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known. Real production fields rarely offer that. They give you sensor histories with no fault log attached, which is exactly the situation where an anomaly-detection method has to invent its own labels, and where quiet assumptions can slip in unnoticed. We work with the open Volve field data released by Equinor and take two things seriously that such
datasets usually skip. First, we build anomaly labels that are not just patterns in the numbers but are checked against what the field's own engineering documents say can physically go wrong, and we release the
reasoning behind every label. Second, we test whether those constructed labels are learnable at all, using both an unsupervised baseline and a small dual-head model that marks when an event happens and what kind it is, an idea we carry over from earlier work on defect detection in metal parts. The results are honest. An unsupervised detector that never sees the labels still lands on the same regions our rules flagged, which tells us the labels are not arbitrary. A compact supervised model recovers event presence and event type well across wells it has never seen, and locates events in time only roughly. We report what worked, what did not, and every assumption in between. The
dataset, grounded labels, per-label provenance, baseline scores, trained model, and code are released publicly under CC-BY-NC-SA 4.0.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Nonvisual Classification of Ground-Condition by Artificial Proprioception in an Amoeba-Inspired Autonomous Walking Robot
Hyoto Yamaguchi, Zenji Yatabe and Seiya Kasai
Nonvisual classification of ground condition based on a
multimodal sensing approach was investigated for an amoeba-inspired autonomous walking
robot. To classify ground condition without image sensing and processing, we implemented artificial proprioception by integrating a three-axis accelerometer, eight foot pressure sensors, and reservoir computing (RC). Even when large fluctuations in the sensor outputs are caused by dynamic motions of a four-legged
robot in walking, our system can classify the ground condition, flat or rough, with high accuracy. We demonstrate on-site switching of walking gait depending on ground condition in the
robot. We also discuss the contribution of each sensor to ground condition classification.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Jiaxuan Li, Qing Xu, Xiangjian He et al. (+4 more)
Cross-modal
alignment of visual and textual representations is fundamental to
multimodal medical image understanding, yet remains hindered by uncertainty in both modalities under real-world clinical conditions. Existing
vision-
language segmentation methods rely on deterministic cross-modal matching, which overlooks aleatoric uncertainty from ambiguous boundaries and epistemic uncertainty from limited training data, leading to fragile performance under domain shift. To address this issue, we propose DistMedVL, a probabilistic
vision-
language framework that introduces a lightweight Probabilistic Cross-Modal Adapter (PCM-Adapter) upon frozen encoders to explicitly model representational uncertainty. Specifically, the PCM-Adapter comprises two sequential modules for progressive probabilistic
alignment. We first devise a Mahalanobis
Alignment Module (MAM) that models textual
tokens as Gaussian distributions and computes patch-text compatibility via Mahalanobis distance, yielding variance-conditioned matching that downweights unreliable feature dimensions. Moreover, we devise a Distribution Flow Module (DFM) that estimates modality-wise confidence parameters and performs
vision-guided refinement of textual distributions, accommodating distributional variation across imaging modalities. Extensive experiments across eight medical
segmentation benchmarks demonstrate that DistMedVL outperforms state-of-the-art methods with only 6.3M trainable parameters, exhibiting superior data efficiency, perturbation robustness and cross-
dataset generalization.
Read the full abstract ▾
All authors Jiaxuan Li, Qing Xu, Xiangjian He, Yue Li, Daokun Zhang, Fiseha B. Tesema, Rong Qu
Artificial Intelligence
A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition
Jiaheng Chen, Jiaxing Li, Tinghe Zhang et al. (+1 more)
Trajectory prediction has shifted toward structured formulations with explicit social modeling. However, existing methods inadequately distinguish the functional roles of social influence in trajectory planning. Observing that
agents typically form motion plans by anticipating others' future behaviors before making local reactive adjustments, we identify social interactions as playing staged roles, namely planning precedes reaction. We propose INTraJ, a unified framework that decomposes social influence into two stages: a planning stage constructs reference trajectories using future social information, and a reaction stage recovers local adjustments from the residual between full-context prediction and the reference. INTraJ supports both multi-target and single-target paradigms. Extensive experiments on four standard
benchmarks, including Argoverse 2, Argoverse 2-ped, ETH/UCY, and SDD, demonstrate consistent improvements, particularly in FDE and long-horizon consistency, with state-of-the-art performance achieved in several settings. INTraJ reframes trajectory prediction as a planning-driven two-stage process, validating that staged social modeling is critical for stable predictions. The code is publicly available at https://github.com/11isnotavailable/INTraJ.
Read the full abstract ▾
All authors Jiaheng Chen, Jiaxing Li, Tinghe Zhang, Chaopeng Guo
Artificial Intelligence · Cross-listed from physics.plasm-ph
SafeDivertor: Faithful Divertor Heat Flux Reconstruction from Macroscopic Plasma State Signals via Time-Frequency Prior Exploitation
Hao Si, Zehua Chen, Qingquan Yang et al. (+8 more)
Divertor heat-flux analysis is essential for understanding
plasma-wall interactions and protecting
plasma-facing components in
magnetic-confinement fusion devices, while conventional infrared-based inversion is usually performed after discharge and requires heat-conduction modeling with device-specific material properties, divertor geometry, and boundary conditions. Rather than accelerating this conventional infrared-based inversion paradigm, we introduce a new online-oriented signal-based reconstruction paradigm that directly reconstructs time-resolved radial heat-flux profiles from multi-source macroscopic
plasma-state signals available during discharge. To enable systematic study of this task, we construct DivMPS2HF, a multi-source discharge
dataset that provides the data foundation and
benchmark for signal-based divertor heat-flux reconstruction. We further propose SafeDivertor, a task-driven framework designed to address the key challenges of signal-based heat-flux reconstruction. It employs physical prior-aware initialization to provide radial-distribution guidance for target channels, input perturbation to reduce over-reliance on specific heterogeneous signals, spectral-aware reconstruction optimization to exploit time-frequency priors and preserve transient dynamics, and progressive training to stabilize the optimization of these complementary objectives. Experiments on DivMPS2HF demonstrate that SafeDivertor achieves the best overall performance among the evaluated time-series baselines across all five metrics, establishing a new performance
benchmark for signal-based divertor heat-flux reconstruction. The source code will be released on https://github.com/Event-AHU/OpenFusion
Read the full abstract ▾
All authors Hao Si, Zehua Chen, Qingquan Yang, Xiao Wang, Dengdi Sun, Wanli Lyu, Gaoting Chen, Guosheng Xu, Hang Su, Jin Tang, Jun Zhu
Artificial Intelligence · Cross-listed from cs.MA
F$^2$Agent: Financial Fusion of Agentic Intelligence for Multimodal Trading
Changshuo Liu, Yanzheng Jin, Shangfeng Cai et al. (+3 more)
With increasingly diverse and heterogeneous information sources, effectively leveraging
multimodal data is becoming pivotal for high-quality financial trading. Although recent advancements in Large
Language Model (LLM)-based
agents have enabled the ingestion of
multimodal inputs, existing methods fail to capture nuanced cross-modal dependencies and remain vulnerable to
market noise, due to limited
multimodal modeling, ineffective fusion mechanisms, and inadequate robustness. To address these challenges, we propose F$^2$
Agent, a novel
multimodal agentic paradigm driven by the Financial Fusion of Agentic Intelligence. F$^2$
Agent first deploys a hierarchy of specialized
agents to comprehensively extract modality-specific signals. It further introduces a modality-aware adaptive fusion mechanism coupled with noise-robust consistency regularization to dynamically capture fine-grained inter-modality dependencies and generate noise-resilient trading signals. Extensive experiments on six stocks and cryptocurrency assets demonstrate that F$^2$
Agent consistently outperforms 16 competitive baselines across multiple trading metrics, with over 20% relative improvement in annualized return on average. Notably, F$^2$
Agent delivers returns of 120.48% on GOOG and 148.41% on TSLA, demonstrating its efficacy and robustness in varying
market dynamics.
Read the full abstract ▾
All authors Changshuo Liu, Yanzheng Jin, Shangfeng Cai, Peng Fang, Xiaokui Xiao, Beng Chin Ooi
Artificial Intelligence · Cross-listed from cs.CY
Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
Jessica Y. Bo, Paula Akemi Aoyagui, Shalaleh Rismani et al. (+3 more)
Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks favor technical methods, such as model
benchmarks and LLM simulations, often sidelining empirical research with human subjects. To examine this apparent gap in the acceptance of human research, we conduct an expert survey (n=93) and expert interviews (n=17) with AI Safety & Ethics (AISE) researchers from Technical, Sociotechnical, Governance, and Normative backgrounds. Our findings suggest that although there is a consensus that human research is valuable for generating evidence for AISE, its adoption and acceptance are constrained by perceived validity issues, tangible resource barriers, epistemic and personal preferences in methods, and infrastructural constraints from the broader research community. In particular, Technical researchers tend to value human research less and collaborate across disciplines less, suggesting an epistemic tension towards human methods. We propose recommendations for establishing the epistemic fit of human research within AISE and bridging the prohibitive limitations that researchers face, while avoiding performative 'human-washing'.
Read the full abstract ▾
All authors Jessica Y. Bo, Paula Akemi Aoyagui, Shalaleh Rismani, Dipto Das, Syed Ishtiaque Ahmed, Ashton Anderson
Artificial Intelligence · Cross-listed from cs.CL
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Sichun Luo, Yi Huang, Guanzhi Deng et al. (+6 more)
Large
language model (LLM)-driven
evolution has shown promise for program search and
algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However, existing approaches typically allocate models at the level of individual queries or mutation steps, overlooking that evolutionary search is stateful: each generated candidate changes the population from which subsequent mutations are produced. We empirically analyze LLM-driven evolutionary trajectories and find that search progress is strongly front-loaded, early trajectory performance is informative but noisy, and cheap models recover much of the early progress achieved by strong models at lower cost. Motivated by these findings, we propose \model, a training-free framework that shifts budget allocation from individual calls to evolving populations through adaptive population handoff. A cheap model explores multiple trajectories in short blocks allocated by a bandit scheduler. Relay Gain, defined as the marginal improvement of a compact, quality-diverse candidate bank constructed for handoff, serves as the scheduler reward and determines when to hand off. The curated candidates initialize a shared strong model population for refinement. Across four
benchmarks and three budgets, \model achieves the highest mean score in 11 of 12 settings, outperforming competitive baselines. Our results suggest that in stateful search, budget allocation should be organized around the population, not the individual call.
Read the full abstract ▾
All authors Sichun Luo, Yi Huang, Guanzhi Deng, Haibo Wang, Haochen Luo, Lei Li, Zefa Hu, Junlan Feng, Qi Liu
Artificial Intelligence
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer et al. (+4 more)
Test-time scaling improves LLM
reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful
reasoning diversity. Verifier-based selection offers an alternative, but its performance depends on the calibration of an external reward model. We propose a verifier-free breadth–depth refinement framework that uses test-time compute to both explore and improve candidate solutions. The method samples multiple independent
reasoning rollouts, refines each rollout through iterative self-critique and self-correction, and aggregates the refined answers by majority voting. Breadth preserves diverse initial attempts, while depth repairs local
reasoning errors before aggregation. Across AIME24, AIME25, AMC, OlympiadBench, and MATH500, our method consistently improves over greedy decoding, majority voting, verifier-based best-of-$N$, beam search, and lookahead decoding across multiple open-weight models. For instance, with Qwen2.5-1.5B, accuracy increases from the strongest verifier-based baseline to $58.0\%$ on MATH500, and from $25.0\%$ to $32.5\%$ on AMC. These results show that test-time compute can be more effective when used to refine sampled trajectories rather than only to sample more candidates or rely on verifier-guided selection.
Read the full abstract ▾
All authors Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen
Artificial Intelligence
Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying
Shimon Honda, Takuma Miyaguchi, Koji Koizumi et al. (+3 more)
This paper proposes the
Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its expected reduction of epistemic uncertainty about action–outcome relations. The model addresses one part of the Uncertainty Driven Action (UDA) model's open question concerning how changes in uncertainty perception determine action selection. We examine two environmental properties: generalizability, or how far knowledge from one trial extends to neighboring candidates, and outcome discriminability, or how clearly differences among outcomes can be distinguished. We tested the model through simulations and human experiments using a graph-shape guessing task that isolates learning about action–outcome relations under a limited trial budget. Epistemic value followed an inverted-U-shaped relationship with generalizability and increased with outcome discriminability in the simulations. In the human experiments, the subjective value of trying and enjoyment followed inverted-U-shaped relationships with generalizability, while choice behavior reflected both properties. The B-EUR model provides a computational account of candidate-action evaluation within uncertainty-driven design activity and offers implications for constructing prototype sets, framing design problems, and organizing feedback to support informative exploration.
Read the full abstract ▾
All authors Shimon Honda, Takuma Miyaguchi, Koji Koizumi, Takanori Sano, Tristan Briard, Hideyoshi Yanagisawa
Artificial Intelligence
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
Yuru Feng, Yaoqi Chen, Beidi Zhao et al. (+7 more)
Although
agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus require autonomous, on-demand skill
evolution at test time, constrained by limited interaction budgets and a lack of training or validation sets. This setting introduces a severe sparse reward challenge, where outcomes conflate multiple latent failure causes. Under such ambiguity, existing methods that greedily refine a single incumbent skill are particularly vulnerable to an exploitation trap, allowing early misdiagnoses to exhaust limited trials along unproductive trajectories. To address this, we introduce SkillHEX, a closed-loop framework coupling hypothesis-driven self-verification with evidence-guided tree search. SkillHEX translates falsifiable failure hypotheses into executable tests, producing diagnostic evidence as dense reward without additional environment attempts. This evidence guides a search over persistent skill-revision branches, dynamically balancing the exploitation of supported edits with the exploration of plausible alternatives. Evaluated on 87 tasks from SkillsBench, SkillHEX outperforms existing self-evolving methods and achieves an average pass rate of 55.9% and 57.9% using GPT-5.3-Codex and Claude Opus 4.7 under a five-iteration budget, respectively.
Read the full abstract ▾
All authors Yuru Feng, Yaoqi Chen, Beidi Zhao, Qianxi Zhang, Xinjiang Wang, Jianan Lu, Zhirui Wang, Shusen Xu, Zengzhong Li, Qi Chen
Artificial Intelligence
Measuring and Detecting Harmful AI Sycophancy
Bohan Jiang, Dawei Li, Yasin Silva et al. (+1 more)
Sycophantic responses are becoming pervasive in large
language models (LLMs), and prior work has pointed out that some of them could be harmful. This paper focuses on one harmful sycophancy: preference-induced stance reversal sycophancy (PSRS), where a model reverses an initial stance merely to align with a user's stated preference. While existing research mainly measures how sycophantic a model is, we go further and ask whether PSRS can also be detected automatically from a single response. To investigate this at scale, we introduce CAP (Contrastive Anchor Probing), a framework for collecting labeled PSRS data. Applying CAP to 17 open- and closed-source LLMs, we collect 290,460 labeled responses across 12 everyday-advice domains. We organize our study around three research questions. (1) How often does PSRS occur? (2) How well can it be detected? (3) How does detection generalize to unseen models? We first reveal that PSRS rates range from 5% to 56% across LLMs, with more capable models being less sycophantic. Next, we show that detecting PSRS is feasible from the response text alone, and detectors need to learn subtle PSRS patterns from the training data. Because new LLMs appear rapidly, detectors inevitably encounter unseen models, making cross-model generalization an important framework goal. We demonstrate that detection performance drops on unseen models and propose an initial approach to address this challenge. We will release our
dataset and code to support future research.
Read the full abstract ▾
All authors Bohan Jiang, Dawei Li, Yasin Silva, Huan Liu
Artificial Intelligence · Cross-listed from cs.LG
GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification
Yunping Shi, En Yu, Kairui Guo et al. (+1 more)
Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion can mitigate such incompleteness, but existing methods operate at a coarse modality level and thus cannot retain reliable components while suppressing misleading ones within the same recovered modality, compromising prediction reliability. To address this issue, we propose GAUGE, a lightweight counterfactual gating framework for incomplete
multimodal classification. GAUGE first imputes missing modalities with a frozen imputer and encodes observed and recovered inputs uniformly as fine-grained evidence units. Rather than intervening on each unit explicitly, GAUGE scores the counterfactual effect of replacing every unit with a reference representation through prediction-aware Taylor evidence scores, all obtained in a single forward-backward pass. These scores are mapped to continuous gates, which are converted into additive
attention-logit biases for unit-wise evidence modulation without altering the backbone architecture. Experiments across six
benchmarks demonstrate that GAUGE outperforms strong baselines across diverse incomplete-input settings. Furthermore, a Taylor remainder theoretical analysis characterizes the error of the first-order approximation relative to the exact counterfactual effect, establishing GAUGE as a principled and scalable framework for fine-grained evidence control under modality incompleteness.
Read the full abstract ▾
All authors Yunping Shi, En Yu, Kairui Guo, Jie Lu
Artificial Intelligence · Cross-listed from cs.CL
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Xingyu Tan, Xiaoyang Wang, Qing Liu et al. (+4 more)
Large
Language Models (LLMs) increasingly act as
agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time. As skill libraries grow, a central challenge is to expose the smallest sufficient executable context under a limited context budget. Existing systems struggle to reuse routines below the whole-skill level, preserve procedural contracts during compression, keep compressed routines executable and expandable, and update the compressed library as skills evolve. These challenges reveal a unit mismatch: skills are retrieved as packages, compressed as text, and converted into execution graphs only after
retrieval, whereas reliable reuse requires a contract-bearing procedural unit. We propose SkillZip, an execution-aware procedural abstraction framework that performs contract-preserving compression over section-level graphs. SkillZip rewrites recurring contract-valid motifs into reversible ported macros while preserving boundary signatures, dependency closure, verifier reachability, and source-level expansion. At inference time, it hydrates a compact, dependency-closed context and expands macros only when required. ReZip further integrates new skills and revises risky macros using execution evidence. Comprehensive experiments1 on technical and
embodied agent benchmarks show SkillZip consistently outperforms the strongest baseline by up to 12.2 points, while achieving a 3.46x compression ratio with 99.2% dependency preservation and 98.7% verifier reachability. Scaling analyses further confirm robust
retrieval across skill libraries ranging from 200 to 100K skills.
Read the full abstract ▾
All authors Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang
Artificial Intelligence
Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflows
Nimisha Karnatak, Max Van Kleek and Nigel Shadbolt
Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled. This raises a central question for responsible AI: under what conditions is reliance on generative AI outputs epistemically warranted rather than behaviourally induced? Existing frameworks largely ask whether AI outputs are accurate, fair, explainable, safe, or trusted by users. These questions remain necessary, and each can contribute to warranted reliance. However, they do not directly specify warranted reliance as a distinct evaluative target: the conditions under which users are justified in treating AI outputs as inputs into their own
reasoning. We argue that this requires an account of epistemic trustworthiness: what makes a system epistemically worthy of reliance. Drawing on philosophical accounts of trustworthiness as competence and audience-orientation, we develop a constitutive normative framework comprising three jointly necessary and non-fungible conditions. First, epistemic humility requires systems to represent and communicate the limits of their competence. Second, epistemic access requires systems to enable users to inspect, question, and contest outputs in context. Third, resistance to epistemic injustice requires systems to recognise users as legitimate epistemic
agents and avoid marginalising their knowledge and experience. Through real-world case analyses in legal
reasoning, medical
reasoning, and hiring, we show how failures of epistemic humility, epistemic access, and resistance to epistemic injustice can produce consequential harms that standard measures of accuracy,
fairness, and usability do not address on their own. We conclude by outlining design and evaluation implications for GenAI systems organised around epistemically warranted reliance rather than output correctness alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Yingqing Guo, Hui Yuan, Zijian He et al. (+2 more)
Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas reinforcement learning (RL) requires
stochastic rollouts for exploration and optimization. Existing online RL methods for flow models therefore replace the inference-time ODE with a
stochastic differential equation (SDE) during training. Although the ODE and SDE share the same marginal distribution in continuous time, they can behave differently after finite-step discretization. In particular, SDE rollouts often become blurry as exploration noise increases, creating a mismatch between training rollouts and inference-time ODE samples. We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction. Each rollout transition takes an inference-aligned ODE Euler step followed by a
stochastic Langevin correction targeting the marginal at the resulting timestep. The required score is recovered directly from the flow velocity, requiring no additional score model, while the transition remains an isotropic Gaussian with tractable likelihood. We theoretically show that, under suitable conditions, a single Langevin correction step reduces the error of an imperfect ODE Euler step and, under matched randomness, yields a more accurate transition than standard Euler–Maruyama discretization of the reverse SDE. Additionally, experiments on SD3.5-Medium, FLUX.1-Dev, and HunyuanVideo show that LC-GRPO consistently improves reward optimization across text-to-image and text-to-
video tasks, preserves generation quality, and substantially narrows the gap between
stochastic training rollouts and deterministic ODE inference.
Read the full abstract ▾
All authors Yingqing Guo, Hui Yuan, Zijian He, Mengdi Wang, Zheng Ding
Artificial Intelligence · Cross-listed from cs.RO
Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations
He Jiang, Jingtian Yan, Yulun Zhang et al. (+5 more)
Lifelong Multi-
Agent Path Finding (LMAPF) requires repeatedly planning collision-free paths for
agents that continuously receive new goals upon reaching their current ones. While many learning-based planners have been proposed for LMAPF, most rely on oversimplified kinematic assumptions that may overlook motion constraints critical to real-world performance. In this work, we study a more realistic LMAPF model derived from many real-world automated warehouse systems, termed LMAPF-R2, which incorporates robust safety constraints and in-place rotation constraints. These constraints substantially increase coordination difficulty, particularly in highly constrained spaces. To address these challenges, we propose Search-Aided Joint Reinforcement Learning (SJRL). We first augment neural policies with Causal PIBT, a single-step search-based planner that resolves
agents' collisions and propagates their intentions. We then introduce a unified RL formulation that jointly optimizes
agent and environment policies, where the environment policy learns graph edge costs to provide global movement guidance via backward Dijkstra search. Experiments demonstrate that SJRL achieves significant improvements over the strong search-based planner, Causal-PIBT, across multiple high-density maps. We further validate SJRL in a challenging mixed-reality warehouse environment with 8 physical
robots and 248 virtual
robots.
Read the full abstract ▾
All authors He Jiang, Jingtian Yan, Yulun Zhang, Yimin Tang, Tanishq Duhan, Rishi Veerapaneni, Guillaume Sartoretti, Jiaoyang Li
Artificial Intelligence
Q-Reflector: Learning GUI Action Reflection with Generated Conditions
Linqiang Guo, Wei Liu, Li Gu et al. (+2 more)
Mobile GUI
agents require accurate action reflection for reliable long-horizon execution, assessing whether each action was successfully executed and whether its outcome constitutes a valid step toward the task goal. When evaluated as standalone reflectors under a common
prompt, frontier VLMs and specialized GUI models exhibit imbalanced recognition of valid and invalid transitions. We propose Q-Reflector, a standalone reflector based on Qwen3-VL-8B that learns GUI action reflection as supervised structured prediction. Given task context, the executed action, and paired screenshots, it generates pre- and post-conditions specifying the action's prerequisites and intended local effect, then assesses execution success and task validity through a structured rationale and binary verdict. Training combines supervised fine-tuning, teacher-student
distillation, and reward- and preference-based refinement. On 1,082 manually verified AndroidWorld transitions, Q-Reflector achieves 82.16% overall accuracy, exceeding all evaluated baselines and showing more balanced performance than GPT-5.2 and GUI-Owl-1.5-8B. On 117 MobileWorld tasks, Q-Reflector achieves task success rates of 46.15% with GUI-Owl-1.5-8B-Instruct and 35.90% with MAI-UI-8B, improving over no external reflection by 17.09 and 14.53 percentage points, respectively. Under the same condition-generation setting, it outperforms the strongest reflection baselines, GPT-5.2 and Claude Haiku 4.5, by 3.42 and 5.98 percentage points, respectively.
Read the full abstract ▾
All authors Linqiang Guo, Wei Liu, Li Gu, Yang Wang, Tse-Hsun Chen
Artificial Intelligence · Cross-listed from cs.CY
The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions
Hadi Hosseini, Samarth Khanna and Leona Pierce
As large
language models (LLMs) enter high-stakes domains such as healthcare, understanding their moral
reasoning becomes essential. Decisions about scarce medical resources often hinge on judgments of responsibility, particularly when patients' own actions contribute to illness. We investigate how LLMs reason about responsibility and its consequences, tracing their judgments across successive levels, from the behavior, to the resulting illness, to the denial of care. We evaluate a wide range of LLMs, spanning different model families and capability levels, on various clinical vignettes adapted from prior studies. Our results identify a judgment-consequence gap: LLMs largely agree with humans that patients bear responsibility for health-harming behaviors, yet overwhelmingly refuse to let that judgment influence how they allocate scarce resources. Specifically, LLMs default to random allocation, whereas humans consistently favor the less-culpable patient. Compared to humans, LLMs also place greater emphasis on access to information, reducing responsibility judgments when health-risk knowledge is unavailable. These findings reveal that LLMs apply a systematically different moral framework than humans when responsibility and resource scarcity intersect, surprisingly often amplifying normative disagreement with humans as
reasoning capability increases.
Read the full abstract ▾
Artificial Intelligence
SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution
Zhi Han, Chenxi Zeng, Liuhaichen Yang et al. (+3 more)
LLM
agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to verification of complete executions. For skill-augmented
agents, verification additionally requires the procedural knowledge encoded in task-time skills, because this knowledge indicates what evidence to inspect and which failures are task-critical. However, existing judge
benchmarks often expose final responses or static trajectories, and rarely combine task-time skills with directly inspectable artifacts and environments. We therefore introduce SkillTV-Bench, a 681-case
benchmark of real
agent trajectories from 50 tasks across eleven domains, designed to evaluate skill-aware trajectory verification for both LLM-as-a-Judge and
Agent-as-a-Judge methods. Additionally, we propose SkillTV-Evolve, which externalizes verification knowledge as a reusable JudgeSkill that guides an
agent judge to plan targeted inspections and issue evidence-grounded verdicts. On a disjoint development pool, an automated
evolution loop further refines the JudgeSkill using misjudged cases. On SkillTV-Bench, the refined skill increases the same
agent judge's accuracy by 14.8 percentage points. In offline rollout-pool selection, it increases selected-trajectory success from 22.9% with one rollout to 45.5% with ten rollouts. The code and data are available at https://github.com/HanZhi306/SkillTV-Bench
Read the full abstract ▾
All authors Zhi Han, Chenxi Zeng, Liuhaichen Yang, Zihan Guo, Ming Zhou, Yang Li
Artificial Intelligence · Cross-listed from cs.CR
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Jialuo Chen, Lingqi Jiang, Xinhao Deng et al. (+7 more)
Self-evolving skill (SES) systems distill
agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a trajectory-poisoning attack on this promotion process. Our skill-visible black-box attacker can inspect a target skill and contribute bounded evidence, but cannot observe private pools or
evolution logic or edit the skill bank. Artifact poisoning requires Inclusion,
Evolution Attribution, and Realization. Attribution is the distinctive bottleneck: the target behavior must appear causally useful, recurrent, and generalizable before promotion. We evaluate four representative security-effect families using inert canary specifications. At 10% attacker support, across six mainstream LLM evolvers in SkillClaw, PoisonedEvolution embeds target behaviors in 546/600 trials (91.0% SER). On the structurally different Trace2Skill pipeline at the same ratio, it embeds target behaviors in 369/600 trials (61.5% SER), demonstrating transfer across
evolution architectures. In a representative controlled study, three consistent attacker records suffice in a 30-record batch, whereas a single record is much weaker. Ablations identify recurring support, causal framing, and domain-aligned encoding as the main determinants of success. These findings expose evidence promotion as a security boundary for self-evolving
agents.
Read the full abstract ▾
All authors Jialuo Chen, Lingqi Jiang, Xinhao Deng, Xiaohu Du, Jianan Ma, Yunhao Feng, Yuqi Qing, Zhihao Yuan, Linkang Du, Jingyi Wang
Artificial Intelligence · Cross-listed from cs.HC
Turing's First Imitation Game: Design Concepts and a Human-Approximates-Machine Reading
Sharon Temtsin and Christoph Bartneck
This paper examines Turing's 1948 report, "Intelligent Machinery", as an important conceptual source for the later imitation games. Its first contribution is to identify and integrate the design concepts underlying the 1948 chess-based imitation game: the possibility that intelligent machines may make mistakes, the exclusion of irrelevant physical features, the role of the human judge, and Turing's claim that intellectual activity consists mainly of search. The paper's second contribution is to argue that restricting the human contestant to a rather poor chess player increases the role of intellectual search and makes human behaviour more comparable to machine behaviour. This interpretation presents the 1948 game as a human-approximates-machine game and suggests that the imitation game framework can be used not only to ask whether machines imitate humans, but also to examine when human intelligence becomes machine-like under specific task constraints.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
Vibe Compiler: A Research-Logic Synthesis Tool That Runs without Prompt Engineering -Toward Enhancing Metacognition for Sustaining Agency in the Age of Generative AI-
Riichiro Mizoguchi, Tomoki Aburatani, Kento Koike et al. (+1 more)
Used as a capable servant, generative AI has greatly accelerated intellectual work, yet it also risks eroding human epistemic agency by encouraging uncritical acceptance of AI-generated
reasoning. Preserving that agency calls for mechanisms that augment human metacognition during AI-assisted work. We therefore propose the Synthesis-Analysis Reciprocity Model, which views intellectual construction as a reciprocal interaction between two cognitive functions. Synthesis selects and combines the components of the artifact; Analysis evaluates them critically against objective indicators and constrains the Synthesis that follows. Grounded in this model, we present the Vibe Compiler, a research-logic compiler that helps researchers turn vague intuitions (Vibes) into coherent research logic. The system attempts to compile those intuitions against a paper ontology of 16 academic parameters. It treats compilation failures as signs that logical components are missing. Rather than fill those gaps autonomously, it returns reflective questions that
prompt researchers to develop the missing
reasoning themselves. We further characterize the origins of structural gaps along two orthogonal dimensions: cognitive function (Synthesis versus Analysis) and executing
agent (human versus AI). The four resulting types of origin give a principled way to identify where breakdowns in intellectual construction arise. Crucially, our design implements the type in which the AI probes its own synthesized output, itself driven by the user's Vibes, and thereby stimulates human metacognition. This choice raises researchers from passive "Makers" of the output into "Managers" who critically direct and validate what the AI produces. In a prototype on NotebookLM and Gemini, AI behavior depended less on prompting than on the structure of the knowledge supplied. The framework spans a learner layer and a researcher layer.
Read the full abstract ▾
All authors Riichiro Mizoguchi, Tomoki Aburatani, Kento Koike, Machi Shimmei
Artificial Intelligence
Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging
Yu Gu, Zhi Zheng, Yunpeng Ba et al. (+3 more)
Evolution Strategy (ES) is a promising alternative to gradient-based fine-tuning for resource-constrained Large
Language Model (LLM)
reasoning. However, directly applying ES to billion-parameter LLMs is highly ineffective. In such high-dimensional parameter spaces, most random perturbations are nearly orthogonal to useful update directions, leading to unstable optimization. We propose Hyper-ES, a subspace-based ES framework that avoids the weakness of ES in full-parameter search while exploiting its strength in low-dimensional optimization. Instead of asking ES to discover useful directions from random perturbations in the LLM parameter space, Hyper-ES first performs a small number of inexpensive gradient-based fine-tuning runs to obtain descent directions. Although each direction may provide only a limited improvement on its own, their span forms a compact adaptation subspace that captures useful
reasoning updates. Hyper-ES then applies CMA-ES to optimize layer-wise DARE-TIES merging coefficients within this subspace, allowing ES to search over combinations of meaningful descent directions rather than over arbitrary full-model perturbations. We evaluate Hyper-ES on three Qwen2.5-Instruct and DeepSeek-R1-Distill backbones across six mathematical
reasoning datasets. Results show that Hyper-ES consistently outperforms GRPO-LoRA by 1% while requiring 10% fewer space-consuming gradient updates. Code at https://github.com/kuangrepi/Hyper-ES.
Read the full abstract ▾
All authors Yu Gu, Zhi Zheng, Yunpeng Ba, Xialiang Tong, Mingxuan Yuan, Zhenkun Wang