Artificial Intelligence · Cross-listed from cs.CR
Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents
Rui Wang, Chao Wang, Xinchen Wang et al. (+3 more)
Proactive personal
agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect
prompt injection. We show that an external provider need not access private user context, compromise the
agent, or gain additional permissions: by controlling only content associated with its own target, it can redirect an otherwise benign
agent to advance that target, recruit legitimately available user context to justify it, and proactively reduce the friction of adoption. We characterize this failure mode through Target Control, Private Binding, and Prospective Support, which respectively steer what the
agent advances, how it connects the target to the user, and what target-specific assistance it offers next. Across three proactive-
agent environments and six simulated user models, the full attack increases target authorization in all tested environment-user-model combinations, with a macro gain of up to 77.4 percentage points. Controlled replay shows that correct user-target binding is more consequential than additional proposal detail alone, while a multi-turn extension reveals that provider objectives can remain influential even without final authorization by reshaping how the
agent responds to user constraints and resistance. These findings expose a broader trust boundary: capabilities designed to serve the user can be redirected toward objectives originating outside the user-
agent relationship.
Read the full abstract ▾
All authors Rui Wang, Chao Wang, Xinchen Wang, Yufeng Zheng, Binbin Liu, Yaofei Wang
Artificial Intelligence · Cross-listed from cs.SD
Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection
Miao He, Peng Cheng, Zhongjie Ba et al. (+4 more)
Advances in
speech synthesis have made deepfake
speeches increasingly convincing, posing growing threats to security. While self-supervised learning (SSL) based detectors achieve state-of-the-art performance, their computational demands (typically 300M+ parameters) prevent deployment on resource-constrained devices. Existing compression methods, designed mainly for content-centric tasks, struggle to maintain competitive performance when directly adapted to deepfake detection. We propose a Task-Aware Joint
Pruning and
Distillation framework that combines cross-domain knowledge
distillation with movement-guided structured
pruning to transfer forgery-discriminative knowledge and preserve critical structures under aggressive compression. Our framework reduces the model to 31.9M parameters with 6.3$\times$ FLOPs reduction, with an average performance drop of only 1.30% across multiple
datasets compared to the uncompressed baseline, demonstrating strong potential for on-device deployment.
Read the full abstract ▾
All authors Miao He, Peng Cheng, Zhongjie Ba, Qing Wen, Li Lu, Xin Yang, Kui Ren
Artificial Intelligence
Learning from imperfect teachers for low-resource acoustic generalization
Shuanglin Li, Ruxiao Qian, Jian Liu et al. (+3 more)
Knowledge
distillation (KD) improves low-resource acoustic learning by enriching one-hot supervision with the softened predictive distribution of a fixed teacher network. However, a teacher trained with limited or imbalanced annotations may produce a biased distribution whose components are not uniformly reliable. Although this distribution can still encode useful knowledge, direct full-distribution matching may also transfer teacher-induced biases, thereby distorting the student's decision boundary and degrading its generalization performance. To address this limitation, we propose Boundary-Anchored Mass-Partitioned
Distillation (BA-MPD), a logit-based
distillation objective composed of Boundary-Anchored Correction (BAC) and Mass-Partitioned
Distillation (MPD). BAC addresses missing ground-truth labels in the set of the teacher's top predictions by swapping the true label for the lowest-ranked entry of the set, thus keeping the mass and uncertainty of the set unchanged. MPD then distills this corrected distribution through separate losses that enforce relational consistency within the set, balance the mass between high- and low-confidence groups, and weight lower-confidence dependencies. Ultimately, BAC and MPD together suppress harmful ranking errors and noisy low-confidence details, while retaining all useful teacher information. Experiments on two acoustic
benchmarks under multiple label budgets show that BA-MPD consistently improves over supervised-learning baselines and vanilla KD while remaining competitive with strong logit-based KD baselines. Cross-budget results further show that BA-MPD remains effective when the teacher and student models use mismatched label budgets, demonstrating its ability to exploit imperfect teachers across supervision gaps. Implementation available at https://github.com/ShuanglinLi/BA-MPD.
Read the full abstract ▾
All authors Shuanglin Li, Ruxiao Qian, Jian Liu, Haijun Lin, Wenwu Wang, Siyang Song
Artificial Intelligence · Cross-listed from cs.CV
Yunyi Chen, Chenru Wang, Xinyi Ye et al. (+2 more)
Diffusion-based
dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven
diffusion models prioritize density approximation over the discriminative decision boundaries required for downstream tasks. Beyond semantic mismatch, relying solely on density also leads to
geometric coverage loss, where generated samples collapse into a few high-density modes and fail to cover the
manifold's structural diversity. We propose
Manifold-Guided Policy Optimization (MGPO), which reformulates DD as a multi-objective reinforcement learning problem and achieves Dual-Space
Alignment via a pixel-space discriminative reward and a latent-space
geometric reward guided by a class-wise Minimum Spanning Tree (MST). The discriminative reward enforces class separability, while the MST-based
geometric reward encourages generated latents to cover a sparse
geometric skeleton of each class, jointly addressing both failure modes. We further provide an idealized analysis that motivates the MST-based reward, including a Hausdorff approximation bound and a subsampling bound independent of the
dataset size. The reward-modular design extends to structured tasks such as object detection and segmentation by substituting the frozen task reward model. Extensive experiments show MGPO consistently outperforms existing methods, including a +8.0% mIoU gain on segmentation under low-budget settings.
Read the full abstract ▾
All authors Yunyi Chen, Chenru Wang, Xinyi Ye, Zexin Zheng, Chi Zhang
Artificial Intelligence · Cross-listed from cs.SE
StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions
Yongyuan Peng, Zhou Feng, Tongying Wu et al. (+5 more)
LLM
agents combine
reasoning, tool use, and persistent
memory to support work across tasks by reusing stored operational records as premises for later actions. However, environmental or requirement changes can invalidate these records, while existing action review, provenance tracking, and clarification mechanisms may leave the underlying persistent state uncorrected. Our audit of coding-
agent trajectories identifies candidate failure chains in which invalid records are reused, leading to task failures and unsafe modifications. We propose StateWise, a framework for diagnosing and repairing persistent operational state before action execution. StateWise uses record-level counterfactual replanning to identify decision-critical records, then establishes their current validity through reliability checks, read-only verification of machine-observable facts, and targeted clarification of developer-owned intent. Typed evidence grounding binds evidence to specific records and scopes, enabling persistent corrections with repair lineage. The
agent then replans from the repaired state, followed by an independent state-action check before execution. We evaluate StateWise on 150 executable coding-
agent cases across diverse runtime environments, workspace configurations, and repository settings, complemented by cross-model evaluations. Under corrupted persistent state, StateWise achieves 93.3% overall correctness, compared with 38.7% for the baseline
agent, with no unsafe actions. Component ablations, multi-task experiments, and transfer evaluations further demonstrate effective recovery, persistent corrections, and transferability across repositories and tool interfaces.
Read the full abstract ▾
All authors Yongyuan Peng, Zhou Feng, Tongying Wu, Jiahao Chen, Yuan Su, Chunyi Zhou, Tianyu Du, Shouling Ji
Artificial Intelligence · Cross-listed from cs.LG
Pythia: Toward Foundation World Models for Multimodal Time Series
Xilin Dai, Hongzhou Chen, Yifan Hu et al. (+3 more)
Time-series foundation models offer a unified approach to forecasting across heterogeneous domains. Textual context and auxiliary observations provide complementary information about temporal dynamics, yet reusable
multimodal predictive representations remain underexplored. We introduce Pythia, a foundation world model that learns context-conditioned latent dynamics across
datasets through a joint-
embedding predictive architecture. A stop-gradient numerical reference guides contextual corrections to predicted future states. A separate probabilistic decoder then adapts to the frozen predictive representation and observed history, decoupling world-model pretraining from observation-space forecasting. On MUSE, Pythia-Tiny's normalized mean absolute scaled error (MASE) and weighted sum
quantile loss (WSQL) are 0.6879 and 0.4269, reducing errors by 6.26% and 5.00% relative to the strongest model evaluated in the published MUSE leaderboard. Through a series of controlled experiments, we investigate how to design a time-series world model through shared pretraining and how joint-
embedding predictive learning can incorporate
multimodal information. The results support separating predictive representation learning from probabilistic readout and show complementary contributions from entity descriptions, events, and
covariates.
Read the full abstract ▾
All authors Xilin Dai, Hongzhou Chen, Yifan Hu, Yiding Liu, Zewei Dong, Jiang-Ming Yang
Artificial Intelligence · Cross-listed from cs.GT
Settling the Computational Complexity of Max-Min Allocation with Ternary Valuations
Thi Ngoc Anh Vu, Trung Thanh Nguyen, Khaled Elbassioni et al. (+1 more)
We study the problem of computing an allocation of indivisible items that maximizes egalitarian welfare, i.e., the utility of the worst-off
agent, when
agents' item values or marginal values belong to a small set. For additive valuations with values in $\{p,q\}$, where $q>p>0$ and $\gcd(p,q)=1$, we give a
polynomial-time
algorithm when $p=2$ and prove constant-gap hardness when $p\geq3$, already with exactly three high-valued goods per
agent. We also give an $\sqrt{3/2}$-approximation for common positive bi-valued additive valuations. For mixed additive valuations in $\{-p,0,c\}$, where $p\in\{1,2\}$ and $c$ is a positive integer, a reduction to maximum-weight perfect matching resolves the conjectured tractability of $\{-2,0,c\}$-valuations. For submodular valuations with marginals in $\{-2,0,c\}$, where $c$ is odd, we establish an exact unit-gap hardness result and exponential value-query lower bounds, even when all but one
agent are additive. Finally, for $\{-1,0,1\}$-submodular valuations, we prove that no finite multiplicative approximation exists unless $\p=\np$. Together, our results resolve open questions and provide a complete picture of the computational complexity of max-min allocation with ternary valuations.
Read the full abstract ▾
All authors Thi Ngoc Anh Vu, Trung Thanh Nguyen, Khaled Elbassioni, Jörg Rothe
Artificial Intelligence · Cross-listed from cs.LG
EMG-GPT: Predictive Pretraining on Residual-Quantized EMG Tokens for Hand Pose Estimation
Ettore Magni, Rolandos Alexandros Potamias, Stefanos Zafeiriou et al. (+1 more)
Surface electromyography (sEMG) is a low-power, cost-effective biosignal for hand-pose estimation and gesture classification. In this work, we examine whether self-supervised pretraining on sEMG can yield transferable representations for continuous hand-pose estimation. We introduce EMG-GPT, a causal
transformer-based model that operates on discrete sEMG representations from a frozen residual vector quantization (RVQ) tokenizer and learns temporal dynamics through depth-autoregressive future-code prediction. The model combines within-frame integration with causal temporal modeling while preserving the geometry of the pretrained codebook. EMG-GPT shows competitive results in both Regression and Tracking tasks, supporting EMG-only pretraining as a viable approach for learning transferable sEMG representations.
Read the full abstract ▾
All authors Ettore Magni, Rolandos Alexandros Potamias, Stefanos Zafeiriou, Konstantinos Barmpas
Artificial Intelligence · Cross-listed from cs.RO
Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
Yifan Li, Jiaxu Wang, Dongming Wu et al. (+4 more)
Most
vision-
language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise representation wastes capacity on highly correlated neighboring actions, leaves temporal continuity and smoothness to be learned implicitly, and forces a tradeoff between long-horizon coverage and the local precision required for contact-rich manipulation. To address these limitations, we introduce Vela, a
vision-
language-action foundation model that represents future
robot behavior as continuous trajectories. Vela combines a compact spline-based action representation with motion-dependent temporal support and a shared action interface for heterogeneous embodiments, allowing a fixed output budget to adapt its temporal resolution across motions. We pretrain Vela on large-scale multi-embodiment
robot data and evaluate it on LIBERO-X, EBench, and two real-world long-horizon tasks, egg-cake cooking and potato shredding, obtaining promising results across simulation and physical manipulation. These results highlight the potential of continuous action representations as a foundation for future embodied foundation models. Project page and more results: https://clementine24.github.io/Vela/ .
Read the full abstract ▾
All authors Yifan Li, Jiaxu Wang, Dongming Wu, Yicheng Jiang, Ryan Ji, Xiangyu Yue, Yanwei Fu
Artificial Intelligence
GFGE: Unifying Explainable AI Methods through an Interpretation Framework
Jinfeng Zhong
Explainable artificial intelligence (XAI) encompasses methods that draw on different sources of information and address different explanatory needs. A common framework is needed to describe how this information becomes evidence and is communicated as an explanation for a particular recipient. We propose the General Framework for Generating Explanations (GFGE), grounded in interpretative frameworks and the complementary activities of sense-reading and sense-giving. Its conceptual foundation is the Interpret/Explain Schema (IES), which connects an analyst's interpretation of system evidence, the communication of a selected account, and the recipient's interpretation of that account. GFGE operationalises this schema through five roles: data interpretation, model interpretation, output interpretation, optional post-hoc analysis, and aggregation. A role-typed operation graph records method-specific dependencies, while evidence records retain the sources, assumptions, and limitations of explanatory claims. The explanatory question, audience, and context guide the procedure. We instantiate GFGE for attribution, surrogate, counterfactual, concept and prototype, intrinsic rule, argumentation, and
language-model methods. These instantiations show how intrinsic, post-hoc, and hybrid workflows can be represented through the same roles while preserving their distinct evidential requirements. GFGE provides a common basis for analysing explanation workflows, tracing communicated claims to their evidence, and identifying unresolved explanatory dependencies.
Read the full abstract ▾
Artificial Intelligence
Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
Akash Das and Ishan Roy
The architecture of modern LLMs consists of a profound cognitive polarization. LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mechanism to access the outside world. Agentic frameworks have not bridged this gap; instead, models are often compelled into pathological "induced amnesia." Under the prevailing "Retrieve-Always" paradigm,
agents must distrust their internal knowledge, making every user interaction a "tabula rasa" event that must be checked externally. This creates reflexive dependence that can be thermodynamically wasteful, cognitively fragile, and susceptible to irrelevant context. We propose a return to first principles, operationalizing the biological maxim "Look Before You Leap." We introduce MARTA (Metacognitive Adaptive
Retrieval and Thought Architecture), a neuro-symbolic framework that bridges parametric and non-parametric knowledge. Rather than treating
retrieval as mandatory, MARTA models it as a cost, taking the leap only when perceived internal inadequacy warrants external information. By allowing the
agent to gauge the
entropy of its own thoughts before acting, MARTA enables deliberative
retrieval and uncertainty-aware decision making. Our approach suggests that giving
agents the capacity for introspection can restore a more efficient balance between internal knowledge and external information.
Read the full abstract ▾
Artificial Intelligence
Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
Akash Das and Ishan Roy
Most Large
Language Models exhibit a fundamental tension between two sequential tasks, such as logical
reasoning and safety
alignment. The high-variance internal states required for sophisticated Chain-of-Thought (CoT) deduction can geometrically interfere with latent representations encoding safety constraints. We identify this phenomenon as Sequential Subspace Interference, showing that standard fine-tuning on logical tasks such as multi-step mathematics and code generation can result in a 23.3% interference penalty on
alignment benchmarks, substantially weakening the model's safety priors. This
Reasoning Drift is not adequately captured by current adaptation methods because gradients for logical tasks are rarely orthogonal to safety objectives. To address this issue, we propose AURA (Adaptive Unique Residual Allocation), a spectral regularization framework that enforces Spectral Independence between
reasoning and safety. By explicitly estimating the null space of the
alignment manifold and constraining
reasoning updates to its orthogonal complement, AURA enables models to improve logical
reasoning without compromising safety. Empirically, AURA recovers 23.0% of the lost performance while preserving greater than 0.98 cosine fidelity to the safe state, demonstrating that
reasoning and
alignment can be effectively decoupled through
geometric regularization.
Read the full abstract ▾
Artificial Intelligence
Image Synthesis as an Intermediate for Controllable Time Series Generation
Haochen Yuan, Jing Xie and Yunbo Wang
Semantic-driven time-series generation offers a promising way to improve downstream learning in few-shot forecasting, but directly generating numerical sequences from
language often fails to preserve the intended temporal structure. We propose VisualBridge, which uses time-series plots as a visual intermediate to bridge high-level temporal semantics and numerical sequences. An MLLM first converts plotted series into structured semantic representations, enabling explicit control over temporal properties such as trend, seasonality, and
volatility. We then learn a semantic editing policy with downstream forecasting rewards, allowing the generation process to favor temporal patterns that are beneficial for the target task. The resulting sequences are further modeled by a temporal VAE to produce consistent multivariate augmentations. Experiments on standard public forecasting
benchmarks demonstrate that VisualBridge improves few-shot forecasting over conventional augmentation methods, with ablations validating the roles of visual semantic grounding, learned semantic control, and VAE-based generation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ME
Same Predictions, Different Harms: Causal Auditing of Patient World Models
Yicheng Qi and Xiyi Xiong
Patient world models used for clinical trial simulation can agree on transition kernels and arm-specific risks, yet disagree on the fraction of patients harmed by switching treatment—the counterfactual quantity that matters for intervention-aware
reasoning. We audit this reliability gap in a two-stage shared-response SCM: a categorical intermediate health state is followed by common terminal care. Under independent stages, the sharp harm interval has closed-form endpoints for at most three intermediate states, with an exactness boundary at four states. Declared dependence and response-mismatch budgets yield calibrated outer bounds when stage independence or complete mediation is relaxed; in a symmetric three-state model the entire sensitivity frontier is sharp, $[0,\min\{1/2,1/3+(\rho+\delta)/2\}]$, and shows exactly how budgets erase the gain over endpoint-only bounds. Two eight-variable response LPs propagate interventional uncertainty for finite-sample audits. Exact witnesses verify attainability. On public clinical simulators (EpiCare; sepsis), native configurations show little resolved stage dependence and no additional joint-compatibility gain over pairwise transport—honest negative results for reliability claims. All experiments are locally reproducible; guarantees remain conditional on the stated causal model. The results provide a concrete protocol for deciding when a patient world model is safe to trust for counterfactual harm.
Read the full abstract ▾
Artificial Intelligence
From Scientific Observations to Mechanisms: Benchmarking Hypothesis Generation by AI Scientists
Xiaxun Xie, Qingqing Long, Meng Xiao et al. (+4 more)
Data-driven mechanistic hypotheses are essential to scientific discovery because they explain how underlying processes produce observed phenomena. AI
agents and AI scientists increasingly support scientific data analysis. However, their ability to turn empirical findings into mechanistic hypotheses remains insufficiently examined. To address this gap, we introduce MechHypoBench, the first
benchmark for evaluating whether AI
agents and AI scientists can generate such hypotheses from empirical data. It combines paper-derived mechanisms from 14 scientific fields with real-world
datasets containing 17.98 million records. The construction retains the observational complexity of empirical data while providing a specified underlying mechanism.
Agents analyze the observations and propose open-form hypotheses. We develop an evaluation framework that assesses open-form mechanistic hypotheses through their consequences under withheld conditions. Experiments with general
agents and AI scientists reveal a substantial gap between generated hypotheses and the underlying mechanisms.
Read the full abstract ▾
All authors Xiaxun Xie, Qingqing Long, Meng Xiao, Wei Ju, Yuanchun Zhou, Xuezhi Wang, Hengshu Zhu
Artificial Intelligence
AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems
Ao Tian, Jialong Liu, Daqi Zheng et al. (+7 more)
Large
language model (LLM)-based multi-
agent systems increasingly rely on
memory to transform execution trajectories into reusable procedural knowledge. Yet repeated
retrieval also makes
memory errors persistent:
memory pollution arises when outdated, weakly supported, or spuriously successful procedures become recurring components of future
reasoning. Multi-
agent execution introduces an additional structural risk. Scope collapse occurs when procedural knowledge escapes the coordination scope in which it was shown effective and is repeatedly reused at incompatible decision levels, allowing local errors to influence cascades of downstream decisions. Meanwhile, task-level failures provide ambiguous supervision because they rarely reveal which recalled knowledge was responsible. We introduce AECG, a framework for asymmetric experience consolidation and governance for multi-
agent systems. AECG turns
memory from static experience storage into a dynamic reliability-governance loop, preserving coordination scope and using multi-scale, confidence-aware reliability to detect degradation. It then combines degradation with downstream impact to prioritize high-risk knowledge under a bounded review budget, applies targeted interventions, and reactivates revised skills only after paired replay. Across three multi-
agent frameworks and four
benchmarks, AECG achieves the best score in 11 of 12 framework–
benchmark settings and improves over the strongest competing
memory method by as much as 10.23 percentage points; removing scope preservation reduces accuracy by up to 16.89 points. AECG thereby reframes multi-
agent memory from passive accumulation into auditable reliability governance. Code is available at https://github.com/fenhg297/AECG
Read the full abstract ▾
All authors Ao Tian, Jialong Liu, Daqi Zheng, Xin Sun, Mengting Li, Zhizhao Xiao, Zijian Huang, Honglei Wang, Zijian Hei, Yukun Yan
Artificial Intelligence
CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation
Xuechen Li, Shuai Zhang, Nanxuan Zhao et al. (+1 more)
Inspired by cognitive science, we present CREATIVEFLOW, an analogical generation framework that explicitly models analogical divergent thinking to mitigate creative homogenization in text-to-3D pipelines. Our method derives a series of meaningful yet relationally similar source-target asset pairs, each featuring distinct
geometric configurations. Expert evaluations demonstrate that our framework substantially enhances creative novelty and visual fascination. This workflow and its resulting assets establish a foundational
dataset and
benchmark for future relation-aware 3D model training.
Read the full abstract ▾
All authors Xuechen Li, Shuai Zhang, Nanxuan Zhao, Qing Chen
Artificial Intelligence
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
Tu Nguyen, Matthieu Zimmer, Vu Anh Vu et al. (+4 more)
A safe action is not necessarily a viable one. A frozen
vision-
language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the next move, while feasibility depends on the futures it leaves open. To bring those futures into the decision, we derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation reveals a candidate-dependent feasible-future mass: its support records whether safe completion remains possible under the frozen continuation process, while its magnitude measures how much weighted safe-completion mass remains. Since exact evaluation is impractical online, we develop a selective finite-candidate approximation and establish conditions for recovering the best retained viable candidate. Our alarm-triggered, training-free reranker VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six Safety-CHORES settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. Our approach offers a promising and practical path toward safer task completion, grounded in an exact policy-relative target yet requiring neither policy retraining nor online rollouts.
Read the full abstract ▾
All authors Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang, Jannik Hammel Nielsen, Xuebing Zhou, Haitham Bou Ammar
Artificial Intelligence · Cross-listed from cs.CR
Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection
Jingkai Liu, Yufei Han, Xiaoting Lyu et al. (+2 more)
Long-horizon
agents consume external content, invoke tools, and modify persistent state. Indirect
prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged
prompt injection. We build an automated, feedback-guided attack generation pipeline and apply it to Claude Code and Codex in their native runtimes. The confirmed attacks span eight workflow scenarios, seven attack goals, and six injection surfaces, showing that production
agents are vulnerable to context-aware, multi-step injection over long horizons. Stopping such attacks requires a decision before each consequential action: input screening and completed-run evaluation cannot locate the intervention point, and existing pre-action methods use incompatible units and labels. We therefore formulate boundary action auditing: given initial context, a trajectory prefix, and a fully specified pending message or tool call, an auditor predicts Pass or Block before its effect occurs. Pairing attacked and benign executions yields a 479-pair, 3,112-unit
benchmark. We further propose Path-Aligned Attribution (PAA), a training-free auditor that decomposes pending actions into operative elements and traces what supplied each value and guided each decision. PAA blocks only when the model attributes an unwarranted, material effect on an element to an attacker-reachable source that either provides unqualified steering or conflicts with visible evidence. Under full-
benchmark fail-open scoring with Claude Sonnet 5, PAA reaches 86% Block recall at a 6-8% false-block rate (FBR), whereas ARGUS reaches 44-47% recall at 16-33% FBR. Under the same backend, on the tool calls that all three auditors natively support, PAA has higher recall and lower FBR than VIGIL and ARGUS; all paired 95% confidence intervals exclude zero.
Read the full abstract ▾
All authors Jingkai Liu, Yufei Han, Xiaoting Lyu, Wei Wang, Ting Yu
Artificial Intelligence
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
Ruqing Ning, Haibo Meng, Zhishang Xiang et al. (+4 more)
Long-term
memory enables LLM-based
agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent
memories can also induce sycophancy, causing
agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that
memory-induced sycophancy originates from biased or incorrect
memories and attempt to reduce this risk by filtering such
memories at different stages of the
memory pipeline. However, in the real world, objective and correct
memories can still induce sycophancy, and the same
memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved
memories to support objective and reliable
reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual
reasoning to uncover the potential risk of retrieved
memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved
memory in light of the current task via self-reflection; and (iii) Evidence-Based
Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of
memory. Extensive experiments on three
benchmarks demonstrate that MemAdapter consistently improves
memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.
Read the full abstract ▾
All authors Ruqing Ning, Haibo Meng, Zhishang Xiang, Zerui Chen, Jinsong Su, Xin Wang, Qinggang Zhang
Artificial Intelligence
Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts
Jianghan Shen, Zhenjie Liu, Yue Li et al. (+10 more)
Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases and environment interactions. Given such a skill, we train the executor to execute all required phases instead of focusing solely on the final answer. We therefore introduce Grounded Skill-Following, which requires an
agent to execute a fixed, expert-authored skill across its required phases by grounding decisions in environment observations. To achieve verifiable procedural execution, we formulate each skill as a skill contract combining visible skill instructions with an explicit contract runtime. The runtime specifies required phases, admissible actions, permitted transitions, and accepted termination. This structure provides a dense, verifiable training signal throughout execution. We leverage this by introducing Verified Progress Credit, which assigns rewards upon the initial completion of contract milestones and aggregates them into the trajectory return to guide policy optimization. During rollout, the contract runtime continuously tracks state transitions to provide Contract-State Feedback, which indicates whether the latest action is accepted and guides the
agent toward valid next actions. To measure procedural compliance, we introduce the Protocol Completion Rate (PCR), defined as reaching accepted termination through all required phases, and decouple it from the final Task Outcome. Jointly trained with our framework, Qwen3.5-4B achieves Protocol Completion Rates of 99.27% on Math and 99.96% on Search, while slightly outperforming original baselines in Task Outcome (82.95% and 46.61%, respectively). Controlled studies examine how skill instructions, training signals, and contract-state feedback affect both metrics, while withholding interventions evaluate behavioral dependence on observation content.
Read the full abstract ▾
All authors Jianghan Shen, Zhenjie Liu, Yue Li, Jie Huang, Siqi Luo, Yiming Cheng, Yizhi Yao, Kaijie Zhang, Cheng Tang, Minghui Zhang, Ming Hu, Yirong Chen, Ziyan Huang
Artificial Intelligence · Cross-listed from cs.LG
Cross-Modal Contrastive Learning for the Retrieval of Immunotherapy-Associated Molecular Signatures from Histopathology
Sigrid Vila-Bagaria, Mar Teixidó, Miquel Piñol et al. (+3 more)
Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their identification relies on a costly 10-gene RNA signature. We propose a Cross-modal Contrastive Multiple Instance Learning (CCMIL) framework for cross-modal
retrieval, imputing these molecular signatures directly from standard Hematoxylin & Eosin (H&E) slides. By leveraging a supervised contrastive objective, CCMIL aligns visual morphological patterns with molecular phenotypes into a shared latent space. This establishes an interpretable search-by-case
retrieval engine, enabling pathologists to query a whole slide image to surface transcriptomically coherent neighbors and approximate RNA signatures without genomic sequencing at inference. Our results demonstrate that this
retrieval-first approach captures the continuous phenotypic spectrum of tumor inflammation and yields clinically interpretable
attention heatmaps. Furthermore, the learned representation also supports competitive downstream classification, providing a practical molecular pre-screening strategy.
Read the full abstract ▾
All authors Sigrid Vila-Bagaria, Mar Teixidó, Miquel Piñol, Felip Vilardell, Robert Montal, Veronica Vilaplana
Artificial Intelligence
R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments
Xudong Yuan, Ruyun Xu, Jingtai Yang et al. (+1 more)
Recovering three-dimensional human geometry from electromagnetic measure?ments in a complex static environment is difficult because strong multipath responses from walls, floors, and other objects obscure the weak target per?turbation. We propose R1A-PC, a physics-guided method that reconstructs a 2048-point human cloud from paired complex fields measured with and without the target. Complex background subtraction emphasizes target-induced ampli?tude and phase changes, while the background field remains available as an environmental condition. A frequency-balanced discrete Born adjoint produces a three-dimensional spatial knowledge map. At each of two bounded deformation stages, the decoder combines complex measurement features, background fea?tures, and multiscale physical features queried at the current point coordinates; the second stage queries again after the first coordinate update. We analyze the residual of paired subtraction, the weighted normal-operator structure of the raw adjoint, and the feasible set of the predicted cloud. In a held-out background generated by full-wave simulation under a fixed acquisition geometry, R1A-PC obtains a squared Chamfer distance of 0.001434 m2 and an F-score of 0.963080 at 0.05 m. Compared with TopNet, the Chamfer distance decreases by 70.28%. Removing physical guidance or background subtraction increases the Chamfer distance by 242.06% or 241.18%, respectively. Experiments across background layouts and poses support the complementary roles of paired subtraction and position-dependent adjoint features.
Read the full abstract ▾
All authors Xudong Yuan, Ruyun Xu, Jingtai Yang, Xianzheng Sun
Artificial Intelligence
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
Dongki Kim, Namkyeong Lee, Surag Nair et al. (+7 more)
As
agents rapidly evolve, existing
benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientific domains, constructing and updating
benchmarks requires substantial time, labor, and domain expertise, making it difficult to keep evaluation aligned with advances in
agent capabilities. We address this challenge by investigating whether scientific-
agent benchmarks can be automatically generated and iteratively adapted as
agent capabilities evolve. We introduce AutoSciBench, a framework that represents each task as a high-level concept specifying the scientific domain, data modality, and required
reasoning approach, together with a low-level recipe specifying how the question, environment, and ground-truth answer are constructed and verified.
Agents attempt to solve each task, producing solver trajectories and corresponding judge feedback which AutoSciBench uses to revise the recipe or concept, closing observed shortcuts and shifting tasks toward raw-data re-examination, interpretation of intermediate results, and evidence integration. Experience distilled from completed refinement trajectories further guides new concept generation, allowing lessons from earlier task refinement to inform subsequent
benchmark construction. Starting from existing
benchmarks, we evaluate AutoSciBench across computational biology, materials science, and clinical imaging. Generated
benchmarks reduce average solver accuracy by 22.4 and 25.5 percentage points relative to the human-curated
benchmarks in computational biology and materials science, respectively, while generated tasks receive higher average quality ratings across all three domains, suggesting that scientific-
agent evaluation can adapt as
agent capabilities advance.
Read the full abstract ▾
All authors Dongki Kim, Namkyeong Lee, Surag Nair, Carl Edwards, Xiner Li, Edward De Brouwer, Jenna Lynn Collier, Sung Ju Hwang, Gabriele Scalia, Ehsan Hajiramezanali
Artificial Intelligence · Cross-listed from cs.CV
How Does Geometry Enter Generated Motion?
Weihan Li, Junhao Wu, Yuhan Song et al. (+2 more)
Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how
video generators realize this relationship. We fix the law and the initial state and change only the geometry drawn in the first frame, within matched families of tracks and deflectors, and compare each generated trajectory with the simulator prediction for that geometry. Paired interventions change one thing at a time: a local bump, the height of a barrier, the words of the
prompt, the length of the clip. Across nine image-to-
video models, geometry is preserved and shapes the motion: the speed of the ball follows the drawn undulation of a track. A physical state would carry this response forward, and here the generated motion parts from the law. The mean slope barely accelerates the ball, successive contacts fail to compose through a consistent state, an edit ahead of the ball alters its motion before it arrives, and the ball climbs over barriers higher than its release point. Two global conditions organize the global trajectory: text strongly controls the destination, while clip length strongly controls timing in the open-weight models tested. The pattern persists with photographed first frames. Current
video generation thus behaves as geometry-conditioned motion synthesis whose
evolution of state differs systematically from that of a fixed physical law.
Read the full abstract ▾
All authors Weihan Li, Junhao Wu, Yuhan Song, Xiaofeng Lin, Xinlei Chen
Artificial Intelligence · Cross-listed from cs.LG
Zhejun Jiang and Mijung Park
Masked
Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked
tokens with model predictions. At each denoising step, the decoder chooses which positions are sufficiently confident to commit. Existing decoding methods typically rely on softmax confidence, which can be miscalibrated. We introduce BayesER (
BAYESian Entropy-based Reordering), a post-hoc
Bayesian decoding framework that uses predictive uncertainty to guide
token commitment. In BayesER, we construct a lightweight approximate posterior centered at the pretrained checkpoint, similar to Laplace-LoRA but without training LoRA adapters. We average predictions over posterior samples and use predictive
entropy to prioritize reliable positions. We examine how posterior predictions affect position ordering and
token selection across
benchmarks spanning code generation, mathematical
reasoning, planning, and molecular generation. We show that BayesER reduces sequence-level calibration error while preserving or improving accuracy relative to common decoding schemes, including confidence-threshold decoding. Additionally, a posterior fitted on one code-generation
dataset reduces calibration error on another without refitting, suggesting that
Bayesian uncertainty may provide a transferable signal for more reliable MDLM decoding.
Read the full abstract ▾
Artificial Intelligence
Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory
Amit Vadnere and Aishwarya Lonarkar
Persistent
memory for Large
Language Models (LLMs) has matured rapidly: systems such as MemGPT/Letta, Mem0, and Zep now provide
agents with tiered, temporally-aware, model-agnostic external storage, while the Model Context Protocol (MCP) standardizes access to
memory servers. A less addressed problem is that an identical stored
memory object, retrieved by two different LLMs under otherwise identical conditions, may not be interpreted the same way, factually or emotionally. This paper proposes
memory canonicalization: a write-time pipeline that detects ambiguity, conditional structure, and emotional loading in a raw
memory object and rewrites it into an explicit, structurally disambiguated canonical form, with emotional valence represented as a separate field rather than inferred from tone. We formalize the pipeline, define a companion Cross-Model Semantic Drift / Emotional Consistency Score
benchmark (CMSC-E), and report results from a three-arm pilot using 176 synthetic
memory objects and three downstream model families. We find an uncorrected improvement in cross-model emotional consistency for fully canonicalized
memory relative to raw
memory (+0.050, 95% bootstrap CI [0.013, 0.086], paired t-test p = 0.010), but this result does not survive Bonferroni, Holm, or Benjamini-Hochberg correction across the six comparisons tested. None of the factual-drift (CMSD) comparisons reach significance at any correction level. We report these results as exploratory rather than confirmatory and outline needed follow-up work, including larger samples, independent judge models, human-validated rendering, and preregistration.
Read the full abstract ▾
Artificial Intelligence
LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search
Zhiqing Nong, Liang Wen and Chao-Hsuan Liu
Deep search
agents tackle complex knowledge tasks through iterative
retrieval, multi-hop
reasoning, and evidence synthesis across multiple sources. Existing approaches typically assume relatively stable
retrieval systems and operate over short-horizon tool interaction. However, when
retrieval is sensitive to query formulation, even a semantically appropriate query may fail to surface critical evidence because of mismatched entity names, aliases, or keyword combinations. Recovering from such failures requires repeated query reformulation and longer interaction trajectories. This setting poses a distinct training challenge, as the policy must sustain long-horizon query exploration while managing an expanding volume of retrieved content. We propose LexiHorizon, a framework for training search
agents over long horizons that expands the trajectory context budget, manages accumulated
retrieval content using a window over recent tool observations while preserving the
reasoning history, and introduces an outcome-gated search-effort reward that provides a bounded bonus for tool invocations to trajectories with nonzero answer reward. Experiments on XBench, WebWalkerQA, and BrowseComp-ZH show that the resulting 9B model consistently outperforms both its base model and MiroThinker-1.7-mini, with maximum absolute gains of 8.7 and 23.8 percentage points, respectively. These results suggest that combining an extended context budget with
reasoning-preserving context management benefits long-horizon deep search
agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Richard Lee Kim, Yeongmin Kim, Gyuwon Sim et al. (+3 more)
Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple yet effective
algorithm for test-time
alignment is Best-of-$N$ (BoN) sampling, which draws $N$ i.i.d. samples from a pre-trained
diffusion model and outputs the single highest-reward sample. Despite its empirical success, BoN makes limited use of reward information, as it is incorporated only at the final selection stage without influencing the reverse
diffusion trajectory during sampling. Consequently, BoN sampling does not improve the average
alignment of generated samples and is primarily suited to single-output settings. We propose Best-of-$N$ Guidance (BoNG), a novel method that integrates the principle of BoN sampling directly into the reverse
diffusion process. BoNG performs online BoN selection over denoising particles and adjusts the reverse
diffusion process to steer the particle population toward higher-reward regions during generation. Specifically, by introducing an asymmetric guidance interaction among denoising particles, BoNG uses the current BoN particle as a guidance signal to the rest of the particle population. This particle-level interaction reshapes the sampling process toward higher-reward regions, enabling BoNG to improve not only the final best sample beyond Vanilla BoN sampling, but also the average quality of generated samples. Over 36 empirical comparisons, BoNG achieves the best performance in 29 cases, ranking first in 80.56% of the comparisons against SMC and Vanilla BoN sampling. BoNG also supports multi-output capability, achieving 1.3$\times$ ImageReward score of the latest sample-based guidance method with a 1.6$\times$ speedup. We release the code at https://github.com/aailab-kaist/BoNG.
Read the full abstract ▾
All authors Richard Lee Kim, Yeongmin Kim, Gyuwon Sim, Taekyu Kim, Minsang Park, Il-chul Moon
Artificial Intelligence
SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling
Jeonghoon Park, Seongwoon Jo, Jongwon Lee et al. (+1 more)
Long-form
reasoning makes inference expensive, and speculative decoding mitigates this cost by verifying multiple draft
tokens in parallel. Its speedup, however, can fade as context grows and draft acceptance declines. We focus on
attention-mass dilution: as softmax normalizes over more visible Keys, the mass concentrated on the highest-scoring Keys can decrease. We introduce SharpDraft, a training-free method that counteracts this effect through cardinality-aware Query scaling, without the computational overhead of online adaptation. Under explicit assumptions, we derive an exact top-$k$ mass correction and deploy a closed-form fixed-slope approximation. Across AIME-26, GPQA-Diamond, and LongGenBench Diary, SharpDraft achieves $2.59$-$3.19\times$
geometric-mean end-to-end speedups over target-only autoregressive decoding when applied to DFlash, PARD, and EAGLE 3.1. With DFlash, it improves decoding speed and outperforms full-parameter and LoRA-based online adaptation in end-to-end speedup, while matching the unmodified drafter's reported peak allocated GPU
memory.
Read the full abstract ▾
All authors Jeonghoon Park, Seongwoon Jo, Jongwon Lee, Taesik Gong