Search arXiv⌕ Search

SEARCH · Search arXiv

Search Search arXiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,099 records · Page 61Linked to original sources
arXiv2026

Learning Reusable Agent Subroutines from Experience

Existing methods induce various forms of knowledge from agent traces, from sample workflows to programmatic skills. We propose ARISE (Agent Routine Induction from Successful Experience), which identifies recurring procedures in agent traces and synthesizes them into a reusable library of agent subroutines. Across five tasks in narrative deduction, rule application, and constraint planning, it is shown to be a more effective learning strategy than prompting methods and prose and code artifact induction methods. ARISE outperforms chain-of-thought in all ten model-task settings of the main evaluation. Compared to state-of-the-art methods in agent experience induction, our method scores 6.1 percentage points over the strongest evaluated baselines, and 11.5 percentage points over code-skill induction. In our controlled experiment, ARISE also improves average accuracy by up to 15.6 percentage points compared to formatting the induced knowledge as skills and by up to 19.1 points over rewriting it as code tools.

cs.AI↗
arXiv2026

AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification

Structured financial reporting verification requires connecting reported facts to accounting constraints, reconstructing expected values, and executing numerical checks. We study this problem through XBRL numerical consistency verification and introduce \textsc{AuditFlow}, a graph-grounded multi-agent framework built around an executable symbolic environment. The environment links a reusable US-GAAP taxonomy graph with filing-specific XBRL evidence and provides typed tools for retrieval, traversal, computation, and rule evaluation. Two specialized auditors investigate constraints and filing evidence, while a senior auditor coordinates disagreement-triggered refinement. Deterministic tools produce verification evidence; evidential aggregation combines structured reports, including agent-declared overrides, into final decisions. On a newly collected 1{,}000-instance evaluation set of engine-recorded DQC violations, \textsc{AuditFlow} achieves $87.70\%$ joint audit accuracy with Claude Sonnet 4.6, compared with $68.60\%$ for Single Agent and $86.70\%$ for Checker-only. Component and coverage analyses identify executable verification as the main source of accuracy, while additional gains from agent judgment depend on the backbone and checker coverage.

cs.AI↗
arXiv2026

CoPark: Learning Reactive Parking via Self-Play

Learning a single policy that reaches a goal with high geometric precision while interacting safely with nearby agents poses conflicting objectives. Precision favors commitment to a fixed geometric plan, whereas interaction requires immediate deviation when another agent intrudes, causing policies optimized for one objective to often fail at the other. We study this problem in the context of reactive autonomous parking, where multiple vehicles must reach assigned slots with sub-meter terminal accuracy while remaining responsive to neighboring vehicles throughout the maneuver. We propose CoPark, a multi-agent self-play RL approach built on a residual-policy architecture. A precomputed offline plan provides a fixed action prior, while a residual head learns the reactive corrections. The residual policy learns behaviors under self-play, where data and scripting fall short, while the fixed prior holds the slot-frame geometry that pure policies struggle to reach reliably. The key design is a partner-threat-modulated, channel-asymmetric release of the prior. A continuous threat signal shifts authority of the longitudinal channel to the residual head to enable yielding, while the lateral channel remains anchored to the precomputed reference to preserve sub-meter slot alignment. A closed-loop refinement layer corrects residual terminal error from action-grid discretization. We train our policy on six parking lots and evaluate zero-shot on our new reactive-parking benchmark spanning Dragon Lake Parking (DLP) and DeepScenario Open 3D (DSC3D). CoPark achieves ~70-85% success with only 3-6% collision rate, substantially outperforming classical, imitation-learning, and large-scale RL baselines. Importantly, the results demonstrate emergent interaction behaviors such as reverse-yielding, mid-maneuver yielding, tight-corridor passing, and queuing.

cs.RO↗
arXiv2026

Imagine Before You Draw: Visual Prompt Engineering for Image Generation

Incorporating visual semantic representations as an intermediate step before image generation can reduce the modeling difficulty between text and images, thereby improving generation quality. Recent works such as X-Omni and BLIP3o-Next have explored this direction, but they typically use a two-stage external pipeline: a separate autoregressive model first generates semantic tokens, which are then fed as conditioning to an independent diffusion decoder. When the decoder is conditioned only on the compressed semantic plan, it cannot directly access the original input, which introduces an information bottleneck that limits detail preservation in downstream tasks such as editing. Internal architectures such as Transfusion, BAGEL, and Show-o2 avoid this bottleneck by enabling cross-modal interaction within a single model, but they still face the difficult text-to-pixel modeling gap without intermediate semantic guidance. We propose Visual Prompt Engineering (VPE), which can be seamlessly integrated into such internal frameworks. Specifically, the model first autoregressively generates visual semantic tokens ($e.g.$, SigLIP 2) as "visual prompts" that capture the semantic layout, then generates the full image tokens conditioned on this plan. We validate VPE across class-conditional generation, text-to-image generation, and image editing, covering various token types and model architectures. Results show that VPE can accelerate convergence, raise quality ceilings, and through internal integration, achieve substantially better editing preservation (PSNR: $26.76$ vs. $19.92$) than a matched external pipeline with semantic-only decoder conditioning, while maintaining competitive editing responsiveness.

cs.CV↗
arXiv2026

The BRUIT-FM "open data" noise reduction challenge

The BRUIT-FM Challenge asks participants to reduce ''noise'' --- defined as any signal that masks the signal of interest --- on an open dataset of real and synthetic broadband seafloor seismology data. The dataset includes signals from earthquakes, ocean infragravity waves and seafloor currents. It also includes training datasets of synthetic data with reference solutions. Participants are asked to remove or separate these signals to obtain the best earthquake and seafloor compliance signals. The authors will make a first assessment of the submissions, based on noise reduction, signal deformation and ease of use. Participants are invited to a community workshop, in which they will validate the preliminary assessment and collaborate on a community paper describing the results, identifying promising pathways and proposing new directions. The best results will be added to a new version of the dataset, which will persist as a benchmark for future developments.

physics.data-an↗
arXiv2026

Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios

Speech translation (ST) is increasingly adopted in user applications, yet its evaluation largely focuses on decontextualized testbeds and holistic quality, rather than end users' communication needs. We introduce Ouvia, an evaluation framework for measuring user-perceived usability of speech translation outputs in real-world settings. Ouvia focuses on one-to-one communication: an English speaker needs to convey a request to a Portuguese speaker, and the message is automatically translated. Through a custom web app and multi-phase study design, we collect more than 1,750 such interactions in healthcare and everyday situations, mediated by four ST systems, involving speakers from three English dialects and two genders. We find that modern ST serves people only to a limited extent---only around half of interactions are rated as usable---with significant gaps in reported usability across demographic groups. Moreover, among quality metrics, we find that QA-based evaluation is a substantially stronger predictor of real-world usability than standard approaches. Together, these findings stress the importance of situated, user-centered evaluation frameworks that go beyond holistic quality scores and attend to who the technology serves---and how well.

cs.CL↗
arXiv2026

Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses

Given the increased use of large language models (LLMs) for reading and seeking information and the varying needs and backgrounds of users, direct manipulation of text can be a valuable mechanism for end-user control. However, enabling direct manipulation requires that models generate text consistent with user-requested changes. We focus on one such setting, manipulating the complexity of scientific information, and ask if models can generate multiple summaries along a continuum of text complexity that enable effective user selection and control. Through a within-subjects user study, we identify reliable complexity measures and a criterion for how models should conform to these measures. We evaluate five LLMs of different families, sizes, and reasoning abilities on $557$ scientific queries. We find that while models can vary complexity across responses, most changes remain inconsistent, with models shifting the complexity measures in the correct direction at most $33.67$% of the time.

cs.CL↗
arXiv2026

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

Synthetic histopathology image generation addresses patient-privacy concerns and the growing data demands of foundation models. Existing state-of-the-art histopathology generative models use pretrained Vision Foundation Models (VFMs) as conditioning signals. We show this yields conditioning-dominated diversity: on TCGA-BRCA, 62-75% of their output diversity is attributable to the conditioning signal rather than the learned latent space, while de novo synthesis still requires a VFM at inference. We instead use histopathology VFMs as the latent space itself: their patch tokens are $\ell_2$-normalized on the unit hypersphere $\mathcal{S}^{d-1}$ with strong angular dominance and intrinsic curvature, motivating a Riemannian formulation. We present STREAM, the first framework to apply Riemannian flow matching in the histopathology domain, in two stages: 1) a bridge-type stochastic perturbation that establishes per-token rectifiability on $\mathcal{S}^{d-1}$ for training a Diffusion Transformer, and 2) a novel decoder training design whose noise covariance is anisotropic in the left-singular basis of the per-token tangent-projected velocity-field Jacobian, spending a large robustness budget on its low-response directions and a small one on its high-response directions. Across TCGA-BRCA and TCGA-COADREAD, STREAM achieves state-of-the-art gFID and ranks first on nearly all histopathology-specific metrics as well. Code and a public gallery of generated images are available at https://chokevin8.github.io/STREAM-Patho/.

cs.CV↗
arXiv2026

Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation

Activation steering (AS) has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). AS modulates model behavior in a flexible and lightweight manner by injecting task-specific steering vectors (SVs) into intermediate activations. Meanwhile, recent work has identified emergent misalignment (EM) as an emerging safety concern, whereby finetuning on unsafe examples from a narrow task unexpectedly induces broadly unsafe behavior in unrelated domains. With the increasing popularity of AS, it is pressing yet under-explored to thoroughly investigate whether AS can induce EM. In this paper, we conduct a comprehensive study of activation-steering-induced emergent misalignment. Specifically, (1) we identify a steering vector construction to confirm that SVs derived from a narrow task can indeed induce misalignment across broad unrelated domains. Qualitative measurement further reveals that AS-induced EM may pose more severe safety risks than finetuning-induced EM, i.e., AS elicits more actionable harmful responses with greater semantic coherence than those generated by finetuned models. (2) We characterize the properties of AS-induced EM by analyzing key steering-specific factors, including steering magnitude, the low-rank structure of the steering subspace, and the number of fine-tuning epochs used during steering-vector construction. (3) We evaluate the robustness and sensitivity of AS-induced EM across diverse model families, model scales, target tasks, and intervention layers. Our findings reveal activation steering as a significant yet underexamined source of emergent misalignment and provide an activation-space perspective on emergent misalignment and its safety risks.

cs.LG↗
arXiv2026

AgentWorld: A Data Factory for Training LLM Agents from Multi-Turn Interactions

Training LLMs to act as capable agents requires learning from multi-turn interactions with environments. However, multi-turn interaction trajectories generated by heterogeneous agent runtimes are difficult to transform into structured, high-quality training data that training engines can readily consume. In this paper, we propose AgentWorld, a data factory that bridges heterogeneous agent runtimes and training engines through a Gateway Server and a Data Pool, reframing LLM agent training around a unified data lifecycle from interaction collection to training consumption. The Gateway Server captures multi-turn interactions through an LLM API proxy, while the Data Pool organizes them into standardized step records for curation and training. An interactive dashboard supports trajectory monitoring, step inspection, and data review. In our demonstration, users integrate ready-to-use white-box and black-box agents, trace and curate their interaction data across the pipeline, and extend the factory to new agents and datasets through lightweight configuration. Quantitative experiments across multiple datasets and RL methods demonstrate training support for different agent runtimes. AgentWorld provides a practical foundation for transforming heterogeneous multi-turn experience into training-ready data for LLM agents. Our code is available at https://github.com/AgentR1/Claw-R1 and the demonstration video can be found at link https://youtu.be/Pw47dAOw6B0.

cs.LG↗
arXiv2026

Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs

Large language models (LLMs) provide a powerful reasoning backbone for speech understanding, but integrating continuous acoustic signals into a pretrained LLM remains challenging. A central design question is how to tie speech representations to the LLM's text input space while preserving the continuous variation needed for different speech tasks. In this work, we propose Convex Gate (C-Gate), a speech-LLM bridge that represents each frame as a convex combination of frozen token embeddings. This architectural convex-hull constraint fixes the output codebook while allowing continuous mixtures learned from task supervision. With a Whisper-large-v3 encoder, a partially adapted Qwen2.5-7B-Instruct decoder, and joint training on speech recognition, emotion recognition, and spoken reasoning, C-Gate performs accurate transcription and emotion recognition, our representative semantic and acoustic tasks, through one shared decoder. On text-only benchmarks, the adapted decoder loses instruction-following and MMLU accuracy and matches or exceeds the original model on GSM8K and HellaSwag. We further design analyses and interventions on the trained model to examine where the bridge sequence carries task information and how the decoder reads it. These findings show how fixed text embeddings can support both semantic and acoustic readouts through continuous speech-conditioned mixtures.

cs.CL↗
arXiv2026

Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization

Autoformalization (AF) requires both prover acceptance and fidelity to an informal source, but prover acceptance alone cannot establish fidelity, and expert-validated reference formalizations are costly to obtain. We introduce a reference-free proxy-judge framework, which separates correctness into grounding, statement faithfulness, coverage, and inference, and a theory of how imperfect checks shape iterative refinement. We establish three results. First, for a fixed sequence of candidates, an added proxy's false-positive and false-negative rates bound its effect on the pass-but-wrong rate. Second, damage to a correct formalization requires a false rejection that exposes it to further refinement, and harmful revisions are then retained through unguarded changes, missed changes, or prover progress that overrides judge warnings. Third, a decomposition of the final pass rate distinguishes continued refinement, generation of new candidates, and their success in passing the checks. We instantiate the framework with eight proxies and test these predictions on ProofNet and miniF2F in Lean~4 and on e-SNLI and ProntoQA in Isabelle/HOL. Under single-proxy removal, no prediction written before the runs is contradicted, and all traced breaks follow the identified failure routes. The results connect proxy reliability to the benefits, risks, and limits of refinement without reference formalizations.

cs.CL↗
arXiv2026

SecureClaw: Clawing Back Control of LLM Agents

Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the point where external actions are executed, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that enforces authorization in a trusted executor and keeps raw protected data outside the LLM runtime. Sensitive reads pass through a trusted gateway that replaces raw values with reference IDs. In the evaluated deployment, the gateway also provides short planning summaries that deliberately release selected information, a process called declassification. Writes that change external state follow a PREVIEW$\rightarrow$COMMIT protocol in which only a trusted executor may execute the exact request authorized by policy. The runtime can still plan over summaries and reference IDs, but cannot directly resolve the IDs into secrets or perform side effects. Across the AgentDojo, AgentLeak, and Agent Security Bench (ASB) benchmarks, SecureClaw is the only defense we evaluate in a common harness that simultaneously retains usable task utility and achieves 0% attack success rate (ASR) on ASB, 0.64% ASR on AgentDojo, and 3.23% overall leak on AgentLeak's attacked parity lane, which measures final-output and internal-relay leakage. Code is available at https://github.com/ponyyuhan/SecureClaw.

cs.CR↗
arXiv2026

A Unifying Framework for Concept-Based Representational Similarity

Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions. However, concept alignment remains poorly defined: existing approaches optimize different objectives under the same terminology, obscuring what is actually aligned. We propose a unifying framework that decomposes alignment along two axes: what is aligned (representations vs. concepts) and at what level (instance-wise vs. distributional). This induces four corresponding properties---instance-wise and distributional variants of translation and concept consistency---and reveals precisely which of these guarantees existing methods provide. We further introduce InterVenchA, an intervention-based benchmark that separately measures extraction quality, translation quality, and concept consistency---which we validate against human perception of concept alignment. Using this framework, we show that commonly assumed equivalences between alignment objectives fail in practice: optimizing one property does not reliably recover the others, and, on real embeddings, purely unsupervised objectives fail to recover meaningful instance-level alignment. As a constructive consequence, a model, the Coupled SAE (CoSAE), matches or exceeds specialized alignment methods such as crosscoders and Universal SAEs on their own target metrics, by jointly enforcing the properties identified by our framework without any architectural innovation. Moreover, as little as 1% paired data is sufficient to recover instance-level alignment when anchoring distributional objectives. Overall, concept alignment is fundamentally multi-objective, and progress requires treating it as such. Our framework and benchmark provide the means to define, measure, and compare concept alignment methods on this basis.

cs.LG↗
arXiv2026

Biclique decompositions from Welzl orders

A biclique decomposition of a graph is a partition of its edges into complete bipartite subgraphs. We consider graphs whose vertices can be ordered such that the neighborhood of every vertex is the union of a sublinear number of intervals. We observe that these graphs admit compact representations in the form of biclique decompositions of small size. Here, the size of a decomposition is measured as the sum of the number of vertices of its bicliques. Combining this result with the existence of suitable vertex orderings for graphs of low neighborhood complexity, as proven by Welzl in 1988, we recover and extend several known results up to logarithmic factors. These results include upper bounds on the Zarankiewicz problem, matrix multiplication, quantum circuit complexity, and shortest path algorithms in "well-structured" instances.

math.CO↗
arXiv2026

Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin

Convergence-rate analysis for classifiers is often conducted under either Tsybakov margin or Massart margin. The former is a relatively weak condition that typically yields polynomial rates, while the latter is substantially stronger but can guarantee exponential rates. In this paper, we introduce a new condition, called Boltzmann margin, that bridges the gap between these two regimes. It is weaker than Massart margin, generally stronger than Tsybakov margin, and can imply many of their properties under suitable conditions. We apply Boltzmann margin to the analysis of kNN classifiers and establish the first near-exponential convergence rates for kNN classification. We also present extensions of the main results and provide numerical evidence supporting the main theoretical implications.

stat.ML↗
arXiv2026

P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning

Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for 3D generation powered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate a parametric 3D program that is geometrically precise, semantically aligned and assembly-consistent. We introduce P3D-Bench, a benchmark for parametric 3D generation. Unlike a 3D mesh, a parametric 3D program exposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design's structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D, Image-to-3D and Assembly-3D) and scores each output for executability, geometric fidelity, topology, text-grounded constraints, multiview semantic alignment and part-level structure. We construct P3D-Dataset, comprising 400 text cases, 400 image cases, and 203 annotated assemblies. Our evaluation on 100 cases from each task family yields three key findings. First, multi-part generation is substantially more challenging than single-part modeling, with models struggling to compose individual parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry and part-level structure in parametric 3D generation.

cs.CV↗
arXiv2026

Position: Hippocampal Explicit Memory Is the Cornerstone for AGI

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs toward AGI. The key reason is that the underlying learning mechanism of LLMs is highly analogous to human implicit memory. However, higher-order cognitive functions necessary for AGI, such as long-term strategic planning, metacognition, and symbolic reasoning, heavily rely on hippocampal explicit memory and cannot arise solely from implicit statistical learning. Drawing on findings from neuroscience, I advance this perspective and complement it with computational requirements for artificial explicit memory systems, hoping to foster further research and lay the groundwork for explicit memory integration.

cs.AI↗