Action
-
Build or Adopt? Custom-Built vs. General-Purpose LLM Agent Harnesses for Automotive GUI Testing
2026-10-24 12:32:16Arsham Gholamzadeh Khoee, Ruyu Fu, Jiaqi Wei, Ruikun Deng, Robert Feldt, Dhasarathy Parthasarathy, Yinan YuAbstract
As general-purpose LLM agent harnesses mature, organizations must decide whether to continue developing in-house systems or adopt existing alternatives. We study this decision at Volvo Group for GUI testing of Android-based in-vehicle infotainment (IVI) systems. We compare a production, custom-built harness with two general-purpose harnesses, Claude Code and OpenCode, keeping the tools, accessed through the Model Context Protocol (MCP), and the models the same. We evaluate the harnesses with up to four models on Volvo's IVI test cases and on open-ended tasks in public apps (Google Maps, this http URL), and interview ten practitioners: developers, the product owner, and testers. On Volvo's stepwise IVI tests, general-purpose harnesses match the custom-built harness in success but vary more across runs. Their inference cost per task is 2.6-10.7 times higher, yet the engineering effort they save outweighs this: for a nightly IVI regression suite, total monthly cost, including engineering effort and inference, is 3-66% lower. On open-ended public-app tasks, they succeed more often, mainly because they recover better from incorrect actions. Interviews suggest that external advances can turn an in-house harness into technical debt even without deterioration. Adopting a general-purpose harness shifts maintenance from the agent loop to tools and instructions, but gives teams less control over what the model receives. Regardless of the harness, testers want to inspect the agent's actions and ensure that it follows the prescribed test scenario.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33636
PDF
-
Mix Forcing: Causal Pre-Training via Mixture Attention for Interactive World Models
2026-10-24 10:31:58Zelin Gao, Hao Ouyang, Jiapeng Zhu, Qiuyu Wang, Jingye Chen, Zichen Liu, Xing Zhu, Yujun Shen, Yinghao XuAbstract
While interactive video world models require autoregressive generation, directly adapting pretrained bidirectional video diffusion models into autoregressive ones with teacher forcing can disrupt their visual priors and degrade autoregressive generation quality. In this paper, we introduce Mix Forcing, a causal pre-training paradigm for interactive video world models, implemented with the Mixture-of-Bidirectional-and-Autoregressive (MoBA) attention. Mix Forcing jointly trains a video diffusion model with both teacher forcing and bidirectional training, yielding a strong causal initialization for few-step post-training. In self-attention, Mix Forcing leverages teacher forcing to learn causal next-chunk prediction for autoregressive rollout, while using bidirectional attention to preserve pretrained visual priors. To support online text interaction, Mix Forcing further adopts a chunk-wise cross-attention design that conditions each video chunk on a shared environment prompt and its own local prompt, without exposing future instructions to the current chunk. Following causal pre-training on a 14B image-to-video model, we apply consistency and distribution matching distillation to obtain a four-step autoregressive generator. Experiments on our internal benchmark and public benchmarks, including WBench and SANA-WM-Bench, show that our model achieves state-of-the-art visual quality and timely event following with precise camera control. Notably, our model supports high-fidelity long-horizon generation without quality degradation even over one-hour rollouts. Project page is here: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.33589
PDF
-
HA-DiPO: Diffusion Policy Optimization for Heterogeneous Cooperative Transport
2026-10-24 10:24:37Xuebin Li, Jinpeng Xiao, Zong Chen, Pierluigi Arpenti, Bruno Siciliano, Jiebao Sun, Yiqun LiAbstract
Cooperative transport with heterogeneous legged robots requires coordinating different motion capabilities while supporting an unfixed shared payload. We present HA-DiPO (Heterogeneous-Agent Diffusion Policy Optimization), a hierarchical multi-agent reinforcement learning framework under centralized training with decentralized execution (CTDE). The framework decouples team-level coordination from embodiment-specific motion control: at the high level, a centralized critic uses team-value estimates to jointly train independent coordination policies, aligning robot-specific action responses with a shared transport objective; at the low level, embodiment-specific robust motion policies track the coordination commands. The high-level diffusion policies offer more flexible action distributions than single-Gaussian parameterizations, allowing potentially multimodal coordination responses to be represented. The coordination policies learn from scratch through reward-driven simulator interaction without demonstrations. At execution, each robot generates coordination commands using only local robot and payload observations, without partner-state inputs or inter-robot messages. Simulation comparisons show that HA-DiPO achieves higher final mean returns and velocity-tracking success rates, as well as lower velocity errors, than the evaluated baselines. Real-world experiments further demonstrate quadrupedal-wheeled-legged and human-robot cooperative transport.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33584
PDF
-
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
2026-10-24 09:38:02Yihao Hu, Zhihao Wen, Yitong Lin, Siyuan Lu, Pan Wang, Wei Wu, Jiang-Ming Yang, Tao LinAbstract
Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-step dependencies or contain actions that are unjustified by the information visible to the agent at decision time. We identify two coupled requirements for effective trajectory supervision: compositional coverage, so that important observation-action dependencies are represented, and decision grounding, so that each supervised action is supported by the learner-visible interaction history. We introduce Trajectory2Gym, which constructs executable interactions around under-supported compositional structures and derives supervision only from grounded decisions in their realized executions. Structural-support selection allocates the resulting experience, while parent-normalized supervised fine-tuning preserves the semantic interaction as the unit of training weight. This reframes trajectory generation as the deliberate construction of learnable interaction experience, rather than the collection of successful trajectories. Across five Qwen3 scales, Trajectory2Gym improves Tau1, Tau2, and BFCL at every tested scale, increasing the equal-weight three-benchmark mean by 16.9-29.8 percentage points. The gains are strongest in stateful and multi-turn interaction, where later decisions depend on earlier observations and feedback. Our results suggest that scaling tool-use agents depends not only on collecting more successful trajectories, but on constructing interactions whose dependencies are represented and whose decisions are learnable from the agent's visible history.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33568
PDF
-
WorldFailBench: Do World Models Understand Policy Failures?
2026-10-24 09:33:52Zheng Zhang, Xiaoyang Tang, Shuaiqi Cheng, Jiakai Huang, Zhongbo Wu, Ziyi Zhang, Yuan Si, Zeyu Liu, Weibo Gao, Shunyu Liu, Shan You, Fei Wang, Xiaogang Wang, Dacheng TaoAbstract
Robot policy evaluation informs deployment decisions and policy improvement, but physical testing and simulator preparation require substantial effort. World models offer a complementary route through closed-loop interaction in generated environments. Recent benchmarks have demonstrated their potential as policy evaluators through outcome-based evaluation (i.e., assessing task success or failure). However, such evaluation does not establish whether world models faithfully simulate how policies fail. Misrepresenting failures can lead to incorrect diagnoses of policy weaknesses and make policies appear ready for deployment even when small scene changes cause them to fail. We therefore ask: do world models faithfully simulate how and at which stages policies fail, and under what conditions they transition from success to failure? To answer this question, we introduce WorldFailBench with three evaluation tasks. Failure reason tests whether models reproduce the observable errors policies make. Failure stage assesses whether failures concentrate at the same stages of full-task execution. Failure boundary examines whether models reproduce the conditions under which policies transition from success to failure under controlled scene changes in simulation. The benchmark covers manipulation tasks in the LIBERO and RoboTwin simulation environments and real-world manipulation tasks performed by the G1 humanoid robot. Experiments across seven world models reveal substantial gaps in their understanding of policy failures, providing guidance for developing more reliable world models for policy evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33565
PDF
-
Cross-Scale Sparse Attention for Referring Segmentation in Remote Sensing
2026-10-24 09:07:03Yuxi Li, Lu Si, Xia Liao, Yidong Shen, Zheng Wei, Jun Zhang, Xin YuanAbstract
High-resolution remote sensing (RS) imagery provides fine spatial detail over large areas, making it essential for fine-grained scene understanding. Referring Remote Sensing Image Segmentation (RRSIS) aims to segment regions described by natural language, yet many existing methods rely on sequential alignment--fusion pipelines with limited joint modeling of cross-scale visual hierarchies and linguistic dependencies. Moreover, dense attention mechanisms struggle with the sparsity and wide spatial dispersion of RS targets, while current datasets offer limited structured evaluation of multi-target references, multi-hop relational reasoning, and multi-granularity descriptions, limiting both model development and evaluation. To address these challenges, we propose a Cross-Scale Sparse Attention Model (CSSAM), which aligns multiscale visual features with complex referring expressions through two key modules. The Cross-scale Modality-aligned Fusion Module (CMFM) performs unified cross-scale cross-modal fusion, while the Dynamic Multimodal Sparse Hybrid Attention (DMSHA) selectively attends to informative visual--textual tokens, reducing dense visual interactions. Furthermore, we introduce M$^{3}$RRSIS-D, a RRSIS dataset explicitly designed around three core reasoning dimensions: multi-target (M$^{1}$), reference-dependent multi-hop (M$^{2}$), and multi-granularity (M$^{3}$) expressions. Extensive experiments on M$^{3}$RRSIS-D and two public RRSIS benchmarks demonstrate that CSSAM achieves competitive performance across accuracy, fine-grained reasoning, and high-IoU localization metrics, validating its effectiveness for complex semantic reasoning in realistic RS scenarios. Code, dataset, and model weights will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33551
PDF
-
Cross-View and Cross-Time Tracking of Crack Evolution in Concrete
2026-10-24 09:06:04Pengru Deng, Jiapeng Yao, Su Wang, Xuhui He, Zhao Wang, Takanori Emaru, Takashi Matsumoto, Xinrun LiAbstract
Crack propagation provides richer information than static crack observations for evaluating structural conditions of concrete infrastructure and planning maintenance strategies. Unlike static crack detection, which can now be largely automated using computer vision, vision-based crack tracking is a coupled cross-view and cross-time problem: the same physical crack must retain its identity as camera viewpoints change, while newly developed growth must be distinguished from existing crack segments in a unified reference view. Existing segmentation and 3D reconstruction methods can recover crack masks or scene geometry, but they do not preserve crack identity across views or quantify temporal extension. To address this gap, this study formulates crack growth monitoring as a cross-view and cross-time crack-instance tracking task and proposes a geometry-assisted, morphology-aware framework. The framework first uses image-based geometric registration to align observations from different viewpoints into a shared structural reference, then applies morphology-aware instantiation to assign physically interpretable crack identities, and finally performs temporal mapping in the unified view to distinguish newly developed growth from existing crack segments. To enable evaluation, a temporally annotated dataset was established and used, covering three representative cracking scenarios: single dominant crack propagation, mixed-mode branching, and multiple-crack interaction, with pixel-level masks and cross-time instance labels. Experimental results show that the proposed framework can establish loose cross-view identity correspondence under changing viewpoints, while strict spatial overlap and growth localization remain limited by early micro-crack segmentability and projection drift, highlighting directions for future crack-monitoring research.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33550
PDF
-
MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation
2026-10-24 08:50:29Jingmeng Zhou, Seson Sun, Binyao Xu, Lingming Zhang, Hanshi Wang, Fudong Ge, Weiming Hu, Jin Gao, Zhipeng ZhangAbstract
Recent vision-and-language navigation (VLN) policies act on their visual history, and an incorrect action can take them off the instructed route. Paired interventions on four VLN policies show that clearing the history doubles pooled success at the onset of a deviation but lowers it on route, while later in a deviation, removing only the off-route frames helps much less. After a deviation, the retained history keeps the policy from turning where a turn is needed, which we call behavioral inertia. We propose MOON, a framework that equips a frozen VLN policy with two lightweight modules, adding less than 1% of its parameters. A deviation judge decides when to forget, raising an alarm that clears the history when it predicts that the agent is off route. A recovery policy, trained with GRPO from alarm states, learns how to move on, turning more of the successes found only by sampling into a single greedy rollout. Experiments on R2R-CE and RxR-CE show that MOON reaches the highest R2R-CE success rate among the compared methods and raises the success rate of its frozen base by 5.2 and 6.0 points, and an ablation with a random trigger indicates that this gain depends on when the history is cleared. Without retraining, MOON also improves zero-shot object-goal navigation on HM3D-OVON. Together, these results suggest that deviation recovery depends on knowing when to forget, not only how to act. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33546
PDF
-
CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
2026-10-24 08:35:39Xufei Shi, Derong Xu, Wei Chen, Yanyu Yao, Zhi Zheng, Tong XuAbstract
Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often remain static, constraining continued adaptation and improvement over time. Recent work addresses this limitation by evolving memory or collaboration based on interaction experience. However, updates to these interdependent components are not necessarily aligned: an evolved workflow may require experience that memory does not provide, while evolved memory may encode guidance that the workflow cannot use. To address this problem, we propose CoEvolve, a skill-centered framework for aligned memory--collaboration evolution. CoEvolve represents reusable local collaboration patterns as skills that link evolving collaboration decisions to their supporting memories. It further compares original and counterfactual trajectories to identify local evolution signals, which coordinate updates to the skill library, skill memory, and executor memories across rounds. Experiments on the ALFWorld and WebShop benchmarks confirm that CoEvolve achieves the best overall performance among the evaluated baselines, while ablation studies further validate the effectiveness of aligned co-evolution and counterfactual-guided evolution.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33539
PDF
-
FraudSociety: A Generative Agent-Based Society for the Financial-Fraud Economy
2026-10-24 08:26:22Keyang Chen, Mingxuan Jiang, Zeping Li, Yiwen Zhao, Yifan Wang, Qiuyang Zhang, Shuaicheng Qi, Yicun Liu, Zhixin Li, Sen Liu, Yinan Jing, Guangnan Ye, Hongfeng ChaiAbstract
Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such large-scale harm requires jointly modeling informational and financial dynamics. Yet existing simulators typically capture only one side of this interaction, leaving a gap in modeling how fraud unfolds in the real world. To bridge this gap, we introduce \textsc{FraudSociety}, the first LLM-agent-based simulator that jointly models these coupled dynamics. It integrates a dynamic social environment for information exposure and communication, persistent financial ledgers that preserve payment and loss histories, and a Need-Intent-Action architecture for civilian decision making. Fraudsters further adapt their communication and financial actions to individual interaction histories and ledger states, forming a closed feedback loop between the two dynamics. We validate \textsc{FraudSociety} across macro-level outcomes, micro-level behavior, and intervention effects. At the macro level, the simulated fraud outcomes closely match real-world patterns across multiple key statistics. At the micro level, it reproduces strong loss concentration, with the top 10\% of victimization records accounting for 81.1\% of total losses, consistent with Canadian Anti-Fraud Centre statistics~\citep{cafc2025annual}. Counter-fraud experiments further reveal variation across intervention strategies, with the best-performing personalized intervention reducing the repeat-payment rate from 49.4\% to 10.9\%. These results establish \textsc{FraudSociety} as both a high-fidelity simulator and a scalable testbed for evaluating anti-fraud strategies under diverse intervention conditions, thereby advancing research on financial fraud and its prevention.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33536
PDF
-
SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents
Abstract
Skill learning enables web agents to reuse prior experience for long-horizon interactive tasks. However, learned skills are typically evaluated in closed environments, overlooking the fact that real-world web deployment involves continuous shifts in invocation context, perceptual grounding, and execution feasibility. To this end, we introduce SkillShift-Bench, the first benchmark for evaluating skill learning with controlled open-environment shifts. SkillShift-Bench simulates Contextual Shift, Perceptual Shift, and Execution Shift across three self-hosted web systems, and evaluates agents with diagnostics covering task success, interaction cost, skill use, and skill failure. Comprehensive experiments reveal systematic robustness degradation under controlled shifts, characterized by lower success rates, higher interaction costs, and more frequent skill failures, with Execution Shift exerting the strongest pressure. We further formulate shifted skill execution as a nonstationary local executability problem and provide both a dynamic-regret analysis and a practical test-time adaptation method, demonstrating the feasibility of improving learned-skill execution without relearning the skill library. Code, tasks, environments, documentation, and the leaderboard are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33528
PDF
-
Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion
2026-10-24 08:08:23Minqian Liu, Yuexi Shen, Heajun An, Qi Zhang, Pamela J. Wisniewski, Sang Won Lee, Jin-Hee Cho, Lifu HuangAbstract
Training large language models (LLMs) for multi-turn strategic persuasion faces two coupled obstacles: (i) realistic simulation of psychologically grounded persuadees, and (ii) dense, faithful supervision for credit assignment in strategic dialogues. Outcome-only rewards are sparse and uninformative about which conversational moves drove success, while LLM-judge process rewards are expensive and decoupled from the underlying interaction dynamics. We address both challenges with a unified framework. First, we introduce PersuArena, a persuasion simulation environment that produces realistic, non-monotonic trajectories. Second, building directly on this environment, we propose Process Rewards via Online Belief Elicitation for Relative Policy Optimization (Probe-RPO), an online RL framework that converts the persuadee's internal state into dense process rewards. At each turn, three introspective probes are read from the frozen persuadee's logits, yielding a multi-dimensional reward signal that is faithfully aligned with persuasion dynamics. With extensive experiments on PersuArena spanning healthcare, financial advising, workplace management, education, and personal relationships, we demonstrate that our Probe-RPO achieves the full acceptance rate of 52.5%, compared with the 35.8% for the strongest GRPO ablation and 25.8% for the best off-the-shelf LLM. We also conduct comprehensive analyses on the generalization across persuadee models and the persuasion dynamics across conversations. Our work offers a promising paradigm that can provide effective process supervision for strategic dialogue.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33527
PDF
-
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
2026-10-24 07:21:41Qiyao Wang, Xinyi Chen, Hongbo Wang, Jiayuan Lu, Jianhang Li, Minghuan Tan, Yuan Lin, Min YangAbstract
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments documented in Office Actions (OAs) across heterogeneous scientific and technical domains. However, existing benchmarks largely focus on static and limited candidate sets, leaving the full search--reasoning--assessment process underexplored. We present PatEx-Gym, the first framework for developing and evaluating agents for patent examination, which integrates three components. First, PatEx-Bench provides 1K realistic examination tasks, two large-scale retrieval corpora containing over 1M patents and 52K scientific papers, and a harness runtime supporting iterative search, document visits, reasoning, and OA generation. Second, we introduce PASS, an annotation-free Prior-Art Agentic Search Trajectory Synthesis framework. Specifically, it exploits document visits as implicit relevance signals and evidence-acquisition anchors to model intra-turn query behavior, inter-turn search progression, and trajectory-level evidence and outcome quality, yielding PatEx-SynData. Third, we train PatEx-Agent at the 4B scale via supervised fine-tuning on the curated trajectories, establishing a lightweight baseline. Extensive experiments show that final decision accuracy alone does not fully reflect examination quality, while prior-art discovery remains difficult even for strong frontier models. Our PatEx-Agent achieves competitive performance against substantially larger general-purpose agents. These results show that training on PatEx-SynData enables a compact 4B model to serve as a competitive baseline for prior-art search and patent examination. We view patent examination as a demanding testbed for agentic search and deep research agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33503
PDF
-
Explicit Frictional Contact Modeling in Neural Garment Simulation
2026-10-24 06:41:28Thanh-Nguyen Truong, Vu-Hoang Tran, Ching-Chun HuangAbstract
Graph neural networks (GNNs) simulate garments efficiently through physics-based self-supervision, but leave body-garment friction implicit or inside training energies, with no friction coefficient $\mu$ to set at inference; retraining the tested GNNs with a coefficient-specific friction term barely responds to $\mu$. Optimization-based solvers decide each contact's stick-slip state from the reaction that governs it, but only by re-optimizing the garment state at every step; a friction term in a one-pass training objective acts as a fixed-weight penalty on sliding, and the trained weights apply no per-contact Coulomb condition at inference. We therefore resolve friction explicitly after prediction: a Modular Contact Operator, attached to a frozen predictor without retraining or an iterative solve, estimates the normal load, applies a closed-form Coulomb correction along a path across body triangles, and propagates the induced motion through the cloth as a linearized membrane wave. On HOOD and ContourCraft, it raises sticking and lowers slip monotonically in $\mu$, tracking a reference solver's response while coefficient-specific retraining stays flat, with low penetration and reference-consistent stretching at an eighth of the solver's runtime.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33492
PDF
-
Incremental Predictive Value of LLM Tutoring Interactions for Student Performance
2026-10-24 06:34:50Zeyu Dong, Mikael Kwame Kuada, Asa Holley Buchakjian-Tweedy, Ibrahem AljabeaAbstract
We evaluate whether semester-level interaction features from a large language model tutor improve assignment-score prediction beyond constant baselines. StudyChat provides 16,851 student-assistant exchanges from two offerings of an undergraduate artificial intelligence course, with outcomes matched to 175 of 203 student-semester records. Six fitted estimators and training-fold mean and median baselines share repeated nested cross-validation. After averaging each student's held-out predictions across ten repeats, Gradient Boosting achieves mean absolute error of 3.023 grade points, versus 3.138 for the median baseline. The paired difference is -0.114, with a conditional 95% bootstrap interval of [-0.245,0.013]. Representation changes and a semester-specific median yield similarly small gains. In the lowest observed-score quartile, however, boosting's error is 7.30 points, versus 8.07 for the median and 6.67 for the mean; Ridge has the lowest fitted-model error at 6.37 despite its worse overall error of 3.331. Scores concentrate near the ceiling: 160 students (91.4%) score above 90, and the lowest quartile contributes 62.1% of boosting's total absolute error. This retrospective comparison shows how baseline choice and error distribution affect predictive value, informing evaluation of student-support tools without establishing a learning effect.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33488
PDF
-
Learning Dexterous Manipulation: Hands, Simulators, Training, and Evaluation
2026-10-24 06:26:18Luai AbuelsamenAbstract
A dexterous hand can change an object's pose without setting it down. This survey covers 113 learning-based methods that attempt it, the hands they run on, the simulators they train in, and how they report results. The field has largely converged on one recipe: reinforcement learning on privileged state in a GPU simulator, distilled into a vision-only student for transfer to hardware. Almost half the corpus trains that way, nearly all of it in one simulator, whose own successors are barely used. A second and faster-growing branch learns from teleoperated demonstration instead, through vision-language-action models, diffusion policies, and systems whose contribution is the collection rig itself. Published work has tripled since 2022. Grasping remains the largest task family and bimanual coordination the fastest-rising, and almost every experiment runs on one of four hands. What the survey adds comes from reading released code and vendor specifications beside the papers. Eight hands that can be bought or built from published designs appear in no method paper here. Where the depth a hand sinks into the object it holds is reported at all, it is not measured in the physics that produced the motion. Section VII proposes a protocol for the unreported quantities; the body gives the counts behind every claim above.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33486
PDF
-
Can One Hear Geometry? Gauge-Invariant Spectral Descriptors for Text-to-B-rep Retrieval
2026-10-24 06:20:11Hongzhu Yi, Hao Liu, Tao Yu, Tiankun Yang, Yujia Yang, Zhenghao Zhang, Tianyu Zong, Zhenyu Guan, Bingkang Shi, Haopeng Jin, Yuanxiang Wang, Zhongtian Luo, Jungang XuAbstract
Text-to-3D solid retrieval requires aligning natural language with precise geometry despite variations in pose, scale, and recording conventions. Existing methods discretize Boundary Representation (B-rep) models into point clouds or meshes, or learn features from faces, edges, and topology, risking information loss or lacking explicit invariance guarantees. We propose a text-to-B-rep retrieval framework based on group actions and spectral geometric invariants, making invariance an explicit constraint on descriptor construction. Specifically, we use group actions to characterize equivalence transformations induced by translation, rotation, reflection, uniform scaling, and contour recording conventions. For sketch-extrusion solids, we construct a fixed 280-dimensional spectral geometric descriptor by integrating geometric information from three complementary levels, including cross-sectional regions, contour boundaries, and extrusion structures. Furthermore, we use descriptor-consistent multi-positive sets and geometric attribute supervision to promote structural alignment between text and solids. On Text-to-3D solid retrieval, our method achieves 88.6% Recall@5, exceeding the previous state of the art by 13.6 percentage points and demonstrating the effectiveness of explicit geometric invariants for precise 3D solid retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33484
PDF
-
MDPO: Multi-constraint Dexterous Policy Optimization with Reinforcement Learning
2026-10-24 06:09:14Ao Zhou, Zongyou Yu, Ke Wu, Tao Xu, Junqiao Zhao, Wenchao Ding, Alois Knoll, Guang ChenAbstract
Dexterous manipulation requires high-dimensional control policies to accomplish complex contact-rich tasks while simultaneously satisfying multiple safety requirements, such as joint limits, unsafe finger configurations, arm collisions, and unstable object interactions. Constrained reinforcement learning (RL) provides a principled framework for incorporating these requirements into dexterous manipulation policy learning. However, existing constrained RL methods for dexterous manipulation primarily focus on cumulative cost constraints and struggle to simultaneously handle multiple heterogeneous constraints during dexterous policy learning. In this work, we propose Multi-constraint Dexterous Policy Optimization (MDPO) for safe dexterous manipulation. We first formulate dexterous manipulation as a multi-constraint policy optimization problem involving both cumulative cost constraints and state-wise cost constraints. Based on this formulation, we integrate multi-constraint projection into the dexterous manipulation policy optimization process. Specifically, we employ constraint-specific policy projections to map the intermediate policy that maximizes task performance onto the feasible regions defined by the cumulative cost constraint and the state-wise cost constraint. Extensive experiments on ReDMan, including safe joint control, finger safety, and grasping tasks, demonstrate that MDPO achieves superior constraint satisfaction while maintaining competitive task performance compared with the baselines. Our code is available at this link.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33480
PDF
-
Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool
2026-10-24 05:36:33Thomas Kimmeth, Avijit Roy, Vivek SharmaAbstract
Propagandistic content increasingly circulates through online news and social media, where readers often encounter it with limited scrutiny, highlighting the need for reliable and fine-grained detection. This paper introduces Propasafe-Hybrid, a sentence-level system that integrates a fine-tuned transformer classifier with LLM-based technique classification to identify, label, and explain specific propaganda strategies. The pipeline generates actionable outputs, including highlighted sentences, technique assignments, and concise rationales, so users can immediately understand why a sentence was flagged and how each label was determined. To control inference cost, Propasafe-Hybrid employs a cost-aware pre-filtering stage that forwards only high-likelihood sentences to LLMs, reducing token usage while preserving the underlying decision logic. Together, these design choices enhance the explainability, efficiency, and practical usability of sentence-level propaganda detection in real-world news environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33464
PDF
-
A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
2026-10-24 05:04:44Shahrooz Pouryousef, Jesus Lopez, Saeefa Rubaiyet Nowmi, Md Mahmuduzzaman Kamol, Moinul Hossain, Muoi Tran, Mohammad Saidur RahmanAbstract
Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. From packet sizes, directions, timing, and burst structure alone, a passive local observer can infer the serving model, the user's prompt category, and the task executed by a collaborative multi-agent system. Yet current evidence is fragmented across separate datasets and settings, limiting reproducibility and comparison. We present, to our knowledge, the first unified measurement study and public benchmark of encrypted LLM traffic across both user--LLM and multi-agent executions. The large-scale benchmark contains 60,000 user--LLM interactions across 10 models and 6 prompt categories, plus 2,838 multi-agent executions covering 10 task categories and two coordination topologies. Using only encrypted packet metadata, we assess the risk of traffic analysis attack by characterizing traffic signatures, identifying the features most associated with leakage, and testing robustness under prompt reformulation, decoding-temperature changes, larger candidate model sets, and partial traffic observation. Model fingerprinting achieves 97.7\% balanced accuracy, prompt-category fingerprinting reaches 76.7\% mean accuracy, and multi-agent task fingerprinting achieves up to 90.7\% accuracy. Prompt reformulation weakens but does not remove model-specific leakage, and task fingerprints remain detectable even from a single agent's traffic.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31877
PDF
