Research

• Reliable request execution in streaming video generation1 paper raises it · 0 address it

  Models often fail to follow incremental user requests while maintaining state consistency in real-time video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• End-to-end deep search in real-world web environments1 paper raises it · 1 addresses it

  Agents struggle to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Evidence-grounded evaluation for audio-visual reasoning1 paper raises it · 1 addresses it

  Existing benchmarks often allow models to exploit textual or unimodal shortcuts, failing to test true multi-modal reasoning.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.CVOct 13▲ 130

  Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

  Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang +3

  City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic vision-language framework that instead casts grounding as active spatial search. Urbex represents a city-scale 3D scene as an interactive multi-view environment, allowing a VLM agent to query landmarks, zoom into local regions, render oblique views, and commit a grounded bounding box. We optimize this tool-use policy with reinforcement learning on CityRefer, using smooth localization rewards and lightweight shaping rewards for efficient exploration. Experiments show that Urbex achieves the best Hit@1 and IoU on CityRefer, supports candidate-free grounding without ground-truth boxes, and is substantially faster than the strongest city-scale ranking baseline. Zero-shot results on STPLS3D-Refer further indicate improved cross-scene robustness.

  CodePDF

  Summarize this
• arXiv stat.MLOct 13

  Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations

  Wonjae Lee, Jiuk Jang, Hyungbin Park

  This paper studies Wong--Zakai convergence and Fourier neural operator learning for stochastic Volterra integral equations (SVIEs) describing random systems with memory. A Wong--Zakai theorem establishes convergence of pathwise solutions driven by piecewise linear approximations of Brownian motion to the corresponding SVIE solution. This convergence provides a foundation for using mirror-padded Fourier neural operators to learn the solution operator mapping initial conditions and driving noise to entire solution trajectories. Numerical experiments demonstrate competitive prediction accuracy and generalization to temporal grids finer than those used for training, while assessing the influence of padding and computational cost. As a follow-up to \citet{LKP:26}, this study extends their operator-learning framework to SVIEs through separate convergence and approximation analyses tailored to convolutional memory.

  PDF

  Summarize this
• arXiv cs.AIOct 13

  ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution

  Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan +12

  We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three competencies, spanning spatial, scene, and temporal reasoning in perception; long-horizon action organization in planning; and point grounding and affordance in execution. The Agentic Data-Model Self-Evolution Engine continuously adapts data strategies to the model's evolving capability state. The Task-Conditioned Adaptive Training Strategy uses task tokens to activate lightweight low-rank residuals over a shared backbone, separating updates from heterogeneous output formats while retaining shared embodied knowledge. Across a systematic evaluation on twelve benchmarks covering three core competencies and five capability dimensions, ABot-ER achieves state-of-the-art overall performance across perception, planning, and execution within a unified…

  PDF

  Summarize this
• arXiv cs.AIOct 13▲ 6

  Choosing LLMs for Strategic Agent Interactions

  Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz, Shiqiang Wang

  Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. However, they only evaluate strategic performance across individual fixed models. In parallel, contemporary LLM routers pick models under quality-cost trade-offs, but with no notion of a strategic structure. They do not account for an opponent that might be unknown, and that can adapt over time and shift the feedback signal. To address this, we extend the game-theoretic evaluations and define strategic selection as the meta game layered on top of the base game. In each round, a strategic selector fields an LLM from a portfolio of models to navigate a game payoff matrix that is latent and learned online. We find that the evaluation signal is game-specific, and that extracting a reliable signal requires a much higher number of seed runs $N$ compared to traditional benchmarking setups. Evaluating across 5 games and 10 LLMs, we show a model's strategic competence varies significantly depending on the game setup and the opponent faced. Building on this, we implement a suite of selector methods and find that approaches…

  PDF

  Summarize this
• arXiv cs.ROOct 13▲ 0

  Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation

  Youpeng Wen, Gang Wang, Tianyu Huang, Weiwei Zhang, Zhijian Huang +3

  A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progress and determine when to advance. To address these challenges, we introduce Orchestra, an agent harness that separates task planning and execution management from action generation. Orchestra decomposes a complete multimodal instruction into ordered subtasks, tracks completed steps, and updates the locations of relevant objects and destinations during execution. It maintains a shared context containing the active subtask, spatial grounding, and recent observations. An action policy uses this context to generate actions, while a separately trained progress evaluator estimates when to advance to the next subtask. To evaluate whether robots trained on atomic instructions and short trajectories can execute longer subtask sequences, we introduce a benchmark named RMBench-Compose. Orchestra achieves a mean success rate of $68.22\%$ across nine RMBench tasks, outperforming Mem-0 by $26.22$ percentage points. On RMBench-Compose, it achieves an Average Success Length (ASL) of $7.35$ subtasks, $2.46$ times that of…

  Code
• arXiv cs.CLOct 13

  Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English

  Jophin John, Michael Hoffmann, Piroska Lendvai, Florent Dufour

  Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as reliably as their standard-language counterparts. We study this question for Bavarian, Standard German, and English using BAVGROUND, a multiple-choice benchmark, where 206 source questions are aligned across all three languages. Across 14 open-weight 7B--10B instruction models, we compare BF16 with 8-bit GPTQ and two 4-bit settings, GPTQ and AWQ. Eight-bit GPTQ remains close to BF16 and largely preserves the relative behaviour of the three languages, while 4-bit quantisation was found to be much less stable. The two 4-bit methods reduce average accuracy by about 1.4--1.5 percentage points and change 11.9--16.0% of BF16 decisions, with changes concentrated on examples where the BF16 model is already uncertain. This instability does not translate into a consistent Bavarian disadvantage. Although Bavarian, a low-resource dialect, has lower baseline accuracy than German and English, the language most affected at 4 bits varies across models and quantisation methods. Calibration further shapes these cross-language…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations

  Jiahui Sun, Ran Bi, Yifei Liu, Xiaolong Zhou, Yishuo Xu +6

  Urban spatial intelligence calls for 3D cities that agents can measure, interpret, and modify across successive tasks. Maintaining such cities as persistent, code-based states requires lightweight acquisition and support for consistent state updates without repeated dense reconstruction. We therefore formulate a new setting for grounded urban world construction: generating large-scale, instance-level parameterized 3D cities from one low-altitude aerial RGB image per region and known camera parameters, while recovering metrically scaled buildings and explicit road geometry and connectivity. We introduce CityCode, an agent-operable representation that unifies metric geometry, urban topology, visual semantics, and 3D assets through persistent entity identities, with dependency-aware versioned execution for validated updates and historical restoration. We further develop Air2Code to construct this representation by combining visual structure extraction with adapted metric depth estimation. To address occlusion and incomplete coverage, recovered structure and observed appearance guide generative completion and subsequent structure-aware 3D generation for buildings and backgrounds.…

  PDF

  Summarize this
• arXiv stat.MLOct 13

  On the Optimality of Random Features under General Conditions: Misspecified Cases and Robust Learning

  Caixing Wang

  Random features provide a standard approach to scaling kernel methods to large datasets by approximating the kernel with a finite-dimensional feature map. Existing works of random feature methods primarily focus on well-specified models and light-tailed noise conditions, leaving a gap in understanding their performance under more general conditions, such as misspecified models and heavy-tailed noise. In this paper, we provide a comprehensive and improved analysis of kernel ridge regression with random features (KRR-RF) under general conditions. In the light-tailed noise setting, we improve upon the worst-case uniform bounds of the feature map used in the previous works and lead to the minimax optimal learning rates with $2r+γ>α_0$, where $(r,γ,α_0)$ denote the regularity of the target function, the effective dimension of the kernel, and the embedding index of the RKHS, respectively. In the heavy-tailed noise setting, we leverage a recently developed Hilbert-valued Fuk-Nagaev inequality and extend the same optimal results under finite weak moment conditions. The additional cost to achieve robustness is a mildly stronger explicit sample-size requirement than in the light-tailed…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Probing the Geometry of Color Representations in Multilingual Language Models

  Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-Idrobo

  Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic? We decompose color representations into two geometric axes: (P1) alignment to perceptual color space, and (P2) cross-lingual symmetry. Analyzing layerwise embeddings across models and multilingual datasets, we find that perceptual grounding is weak: alignment to CIE-LAB peaks in intermediate layers, then collapses toward output layers. Cross-lingual symmetry degrades with depth, suggesting later layers encode language-specific structure. Functionally, we show that geometric properties predict task performance: models achieve 96.7% accuracy on color classification at layers where P1 alignment peaks, with P1 alignment (r=0.70) significantly correlating with downstream capabilities. Our results reveal a dissociation: text-only LMs learn universal color-language geometry, not universal color-perception geometry, providing diagnostics for where perceptual structure is preserved in language models.

  PDF

  Summarize this
• arXiv cs.AIOct 13

  AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents

  Xiangrui Liu, Shuo Tang, Siheng Chen

  Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state. Traditional Rubrics requires Authors to recreate application interfaces, initial records, policy evidence, and outcome checks for each task, entangling business logic with repeated infrastructure work. We introduce AssetForge, an asset-augmented task-construction pipeline that pairs a reusable construction-asset library with task-specific Rubrics. The assets provide application interfaces, world-state components, policy/evidence carriers, and native assertion definitions; the Rubric directs their instantiation for a particular business task. Executable checks and an additional model-based review validate each candidate, return targeted feedback, and support bounded repair before acceptance. On AutomationBench v1.0.6 public-600, fine-tuning Qwen3.6-35B-A3B on 6,000 AssetForge examples yields 41.17% on the official strict pass@1 metric, 4.4 times the 9.33% base score (+31.83 points). With the same backbone and GLM-5.3 supervision, AssetForge reaches 41.17% versus 30.33% for traditional Rubrics, a 10.84-point gain (35.7% relative)…

  PDF

  Summarize this
• arXiv cs.CROct 13

  Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees

  Wenbin Hu, Huihao Jing, Haochen Shi, Yuxuan Liu, Changxuan Fan +7

  Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such models incur high inference latency and are often poorly aligned with customized policies. To address these problems, we present Jev-Guard, a unified model for safety classification and policy routing. We further construct a policy tree over which Jev-Guard performs routing, spanning diverse domains including content moderation, cybersecurity, privacy, and legal compliance. Specifically, Jev-Guard first navigates the policy tree to select the applicable audit policy given the caller's audit context, and then performs safety classification conditioned on the retrieved policies. On 7,033 evaluation cases, Jev-Guard achieves 93.72\% safety accuracy, a mean latency of 58ms, and 93.10\% hierarchical routing accuracy. The full routing-and-classification pipeline averages 240ms. Furthermore, we integrate Jev-Guard into the Hermes harness framework. Across agent trajectories, its separate permission gate cuts mean review time per task from 4.80s for an SFT-LLM judge to 1.33s, with no policy violations are observed…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On

  Yuhan Li, Zhiyu Jin, Yifan Tong, Wenxiang Shang, Benlei Cui +3

  Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D consistency and texture authenticity. Unlike conventional garment-focused VTON methods, VFTON presents unique challenges due to (1) Data Scarcity, which arises from the difficulty of perfectly matching product shoes with models wearing the identical ones, (2) Viewpoint Misalignment, where the target foot pose and source shoe views are always misaligned, leading to incomplete texture information and detail distortion, and (3) Background-induced Color Distortion, where complex material of footwear interacts with environmental lighting, causing unintended color contamination. To address these challenges, we introduce MVShoes, a multi-view shoe try-on dataset consisting of 7305 well-annotated image triplets, covering diverse footwear categories and challenging try-on scenarios. Furthermore, we propose a dual-stream DiT architecture, ShoeFit, designed to mitigate viewpoint misalignment through Multi-View Conditioning with 3D Rotary Position Embedding, and alleviate background-induced…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing

  Pan Yin. Shuai Yang, Yuanhao Liu, Datao Tang, Jialin Li, Hao Wang +4

  Practical remote sensing applications often require both understanding and generation capabilities for the same geographic scene. However, most existing methods address either understanding or generation in isolation, while existing unified remote sensing models' generative ability is limited to text-to-image. To bridge this gap, we propose Omni-RS, a unified framework supporting four remote sensing understanding tasks and five generation tasks. Specifically, we introduce the "Scene-Guided Two-Stage Training" strategy, which first adapts a multimodal large language model to remote sensing understanding and then uses its hidden states to guide a diffusion transformer for image generation. To enable joint learning across diverse generation tasks, we construct UniGen, a unified multi-task generation dataset, by organizing heterogeneous remote sensing data into a unified format. Furthermore, we introduce "Detailed Visual Conditioning", which uses visual conditions encoded by a VAE to guide the generation process, thereby supporting additional generation tasks that require reference images. Extensive experiments demonstrate that Omni-RS performs exceptionally well in understanding…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Over-parameterization Is Neither Robust nor Fragile in Matrix Sensing: A Geometric Theory of Solution Robustness

  Runze Shi, Ziye Ma

  Over-parameterization is ubiquitous in modern machine learning, yet its effect on robustness remains poorly understood. We study this question in matrix sensing, a canonical non-convex problem that can also be viewed, under an appropriate parameterization, as training a two-layer quadratic neural network. We develop a rank-aware robustness theory for the Burer-Monteiro factorization when the search rank k may exceed the target rank r_star, thereby capturing over-parameterization. Our analysis shows that robustness depends jointly on the degree of over-parameterization and the local geometry of the attained second-order stationary point: increasing k generally worsens sensitivity, but stationary points with the same search rank can exhibit substantially different robustness. Motivated by this observation, we propose a trajectory-aware algorithm that uses spectral balancing and randomized sketching to steer optimization toward less sensitive solutions. In matrix-sensing experiments, the method reduces paired sensitivity by 18-29 percent for isotropic operators and 87-89 percent for weak-tail operators, without degrading reconstruction accuracy. These results demonstrate that…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration

  Yevgeny Rakita, Paul Todd, James R. Neilson, Simon J. L. Billinge

  This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations). The importance comes from the requirement to synthesize technologically useful materials, especially those that are kinetically stabilized. Often, it is a science that follows years of trial and error, culminating in (published) successful recipes, but is truly driven by far more (unpublished) failures. The entry into the era of AI provides an opportunity to use learning algorithms to encode rules from multi-dimensional synthesis pathways, regardless of their technological usefulness, and to decode both forward prediction and inverse learning modes. The main incentive is to accelerate material discovery by generating a global knowledge base that can be shared among data agents and contributed to by them. We will focus on several scenarios in the common synthesis process during solid-state synthesis, primarily because these reactions are kinetic in nature and require closer monitoring and control of the reaction history.

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Prompt or Policy? Optimizing Physician Slate Presentations with LLM User Simulators

  Andrei Niculae, Adrian Cosma, Emilian Radoi

  Choosing the right physician is a key challenge for patients seeking medical care. Physician recommendation systems identify relevant doctors, but patients still find it difficult to compare their profiles to make a decision. We formulate slate presentation optimization: given a patient's medical case and a fixed, ranked list of physicians, we generate short, case-specific summaries that make doctors easier to compare, while remaining grounded in the information in their profiles. To optimize physician presentations without relying on real patient interactions, we develop an offline framework that uses persona-conditioned LLMs to simulate patient choices. We generate patient personas from attributes extracted from each medical case and evaluate presentations for factual accuracy, relevance, naturalness and simulated patient choice. We also use a second LLM judge, unseen during optimization, to assess simulator-specific overfitting. We compare automatic prompt-level optimization with GEPA, parameter-level optimization with GRPO, and their combination across two model sizes. GRPO substantially outperforms GEPA in satisfying the full set of constraints, and its gains in simulated…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems

  Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi, Azadeh Shakery

  Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic simulation possible but typically condition on profiles derived from explicit ratings, demographics, and static sources capturing surface preferences while omitting implicit behavioral characteristics such as decision-making style, aspect-level preferences, and domain expertise. We propose SimInter, a pipeline that elicits these attributes via synthetic interviews between two LLM agents, grounded in the user's statistical profile and historical conversational evidence. Before profile enrichment, an audit agent explicitly flags potential fabrication and stereotyping at the turn level. We instantiate and evaluate SimInter on movie recommendation. We simulate 300 ReDial users and, on a matched subset of 100 users, compare SimInter with a statistics-only baseline: SimInter significantly increases the diversity of expressed preference aspects (filtered aspect entropy: 1.619 vs. 0.859; paired d = 0.96, Holm-adjusted p < 0.001). This gain persists when the simulator converses with two trained recommenders, KBRD and UniCRS, under two…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Bayesian Optimization of CVaR with Unknown Hyperparameters

  Valentin Margraf, Jonas Hanselle, Viktor Bengs, Serafima Lebedeva, Eyke Hüllermeier +1

  We study Bayesian optimization of the Conditional Value-at-Risk (CVaR) of an expensive black-box function that depends on a decision and an environmental variable. Existing no-regret algorithms assume that the correct Gaussian process (GP) kernel and its hyperparameters are known. In practice, however, they must be estimated from limited data, often yielding a misspecified surrogate. This is especially damaging for CVaR because misspecification can distort the estimated tail-risk and thus lead to catastrophic decisions. We propose HE-CV-UCB, the first no-regret algorithm for CVaR Bayesian optimization with unknown GP hyperparameters. Given a finite candidate set containing a well-specified model, HE-CV-UCB adaptively eliminates those inconsistent with the observed data, actively queries where the survivors disagree, and returns a design that is robust across the surviving candidates. We prove that it attains cumulative regret matching the oracle rate of CV-UCB up to a factor depending only on the candidate set's size. Across synthetic benchmarks and three real-world applications, HE-CV-UCB achieves competitive performance and frequently outperforms existing CVaR Bayesian…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  AffectWorld: Benchmarking Emotion-Driven Future World Prediction

  Changhao Song, Yacong Chen, Hui Gao, Yazhou Zhang, Peng Zhang

  The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions shape human actions. However, existing world model benchmarks primarily assess physical plausibility and perceptual quality, leaving emotion-driven world evolution largely untested.We introduce AffectWorld, a benchmark that evaluates the chain Emotion-Action-World State through three tasks: World-State Consistency, Emotion-Action Consistency, and Causal Consistency. It comprises 1,498 everyday video samples annotated with plausible emotions, action tendencies, and atomic world-state constraints. A counterfactual subset of 233 samples tests whether changing an agent's emotion under fixed scene and event conditions yields corresponding changes in actions and consequences. We define eight metrics across the three tasks and an additional counterfactual metric, combining automatic visual assessment with human-calibrated VLM/LLM judgments. Evaluations of five SoTA world models (e.g., Cosmos3) required world-state change scores of 0.100-0.280 and counterfactual emotion sensitivity scores of 0.027-0.070 on a [0, 1] scale. These results…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction

  Md Asiful Islam, Fahmida Alam, Mihai Surdeanu

  Guardrail approaches that rely on reasoning-based large language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit reasoning. We introduce LR-Guard (Latent Reasoning Guardrail), an efficient and explainable guardrail that jointly learns structured latent reasoning and on-demand reasoning reconstruction. Our method distills a frozen teacher's analysis of safe and unsafe prompt interpretations and their comparison into compact latent representations. Joint training optimizes these representations for both safety prediction and reconstruction of the teacher's explicit reasoning traces, enabling human-readable explanations without requiring intermediate text generation for every decision. Experiments show that LR-Guard outperforms its explicit-reasoning teacher in most in-domain and out-of-domain settings on safety classification and explanation extraction, while achieving a 19.4x inference speedup at batch size one. Further, reconstructed reasoning traces from the latent information exhibit high semantic similarity to the teacher's explicit reasoning.

  PDF

  Summarize this

• Anomaly detectors30−14.3%
• Adversarial training42−16.0%
• Forecasting time63−18.2%
• Federated learning37−19.6%
• CAD models12−25.0%
• Frontier LLMs380−25.2%
• Inference & serving214−26.2%
• 3D scene127−28.7%