Self-Evolving Visual Agent via Margin Reward
arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool inv
Knowledge catalogue
arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool inv
arXiv:2610.15575v1 Announce Type: new Abstract: Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned
arXiv:2602.12881v2 Announce Type: replace-cross Abstract: We examine how lyric representation shapes computational similarity using four 384-dimensional multilingual MiniLM representations of 7,891 K-
arXiv:2511.21752v3 Announce Type: replace-cross Abstract: Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted i
arXiv:2610.18945v1 Announce Type: cross Abstract: Amortized Bayesian inference uses simulations to perform Bayesian estimation when likelihoods are expensive or analytically unavailable. However, lear
arXiv:2610.20041v1 Announce Type: new Abstract: A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter
ServiceNow Inc. today announced new controls for governing artificial intelligence agents alongside updates to its EmployeeWorks information portal (pictured) that let employees build specialized assi
arXiv:2610.17093v1 Announce Type: new Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On
arXiv:2610.19696v1 Announce Type: new Abstract: Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate throu
arXiv:2603.23305v2 Announce Type: replace-cross Abstract: We investigate the problem of matching networks where both edge weights and node features are correlated following a specific node corresponde
arXiv:2610.14209v1 Announce Type: new Abstract: The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the use
arXiv:2508.16939v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art generative performance but remain computationally expensive at inference, often requiring many discretizat
arXiv:2610.19095v1 Announce Type: new Abstract: Chatbot Arena ranks language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom. Choice theory pre
arXiv:2610.18308v1 Announce Type: cross Abstract: Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic sim
arXiv:2506.04920v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them incr
arXiv:2610.14980v1 Announce Type: new Abstract: We present a generator of Thai klon pad verse, one stanza from a short topic, and evaluate it against human verse on held-out topics. The generator is a
arXiv:2610.15141v1 Announce Type: new Abstract: Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference
arXiv:2610.17192v1 Announce Type: new Abstract: Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large
arXiv:2601.04948v2 Announce Type: replace Abstract: Although recent years have seen significant progress of humanoid robots in walking and running, the frequent foot strikes with ground during these l
arXiv:2610.19505v1 Announce Type: new Abstract: This paper proposes the SKG (Symplectic-Kernel Gradient) reasoning engine for law-induced inference and induction. Laws are a priori; data provide insta
arXiv:2610.14918v1 Announce Type: new Abstract: Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability. C
arXiv:2610.15481v1 Announce Type: new Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agen
arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluat
arXiv:2610.15725v2 Announce Type: cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unau
arXiv:2610.17727v2 Announce Type: cross Abstract: Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look de
arXiv:2610.16412v1 Announce Type: new Abstract: As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summarizi
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Ver
arXiv:2610.19051v1 Announce Type: cross Abstract: Coordinators that act on what they infer about teammates are usually certified by the accuracy of those inferences. We argue that accuracy is the wron
arXiv:2610.20226v1 Announce Type: new Abstract: In cuVSLAM, visual and inertial measurement unit (IMU) residuals are fused in sparse bundle adjustment (SBA) with a weighting fixed by pre-calibrated no
arXiv:2610.18672v1 Announce Type: cross Abstract: Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among me
arXiv:2610.19781v1 Announce Type: cross Abstract: We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete
arXiv:2604.05656v2 Announce Type: replace Abstract: Vision-language-action (VLA) models with flow-matching action heads, such as {pi}0 and {pi}0.5, have become a standard recipe for generalist robot m
arXiv:2610.17860v1 Announce Type: new Abstract: Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and
arXiv:2610.19992v1 Announce Type: new Abstract: Law students are examined through open-text answers: case solutions, essays and memos that apply the law to a set of facts. Such answers are expensive t
arXiv:2610.18745v1 Announce Type: cross Abstract: Large language models increasingly generate Solidity smart contracts that, once deployed, can never be patched, making a single latent fault permanent
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at
arXiv:2610.19327v1 Announce Type: new Abstract: Robotic ultrasound can standardize image acquisition and reduce operator workload and variability, but policy learning remains limited by the lack of re
Maria Curi / Axios: Source: the US FTC issues ~50-page civil investigative demands to OpenAI and Anthropic over safety incidents, safeguarding practices, and consumer protection — - The FTC sought doc
SPACE is the first component of Perplexity's Agentic Runtime Platform. We're open sourcing it to raise the security bar for agentic products. Read the blog: https://www.perplexity.ai/hub/blog/open-sou
arXiv:2610.19465v1 Announce Type: new Abstract: In initialized spacecraft tracking, a short-horizon motion prediction remains available as event support changes. Observation-Aligned Event Innovation (
arXiv:2606.13497v2 Announce Type: replace-cross Abstract: This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatic
arXiv:2610.19876v1 Announce Type: new Abstract: Continual learning aims to acquire new knowledge while retaining previously learned knowledge. However, updating shared parameters when learning new tas
arXiv:2610.19636v1 Announce Type: cross Abstract: Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stake
arXiv:2610.20139v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have emerged as a promising approach to mechanistic interpretability by decomposing language-model activations into sparse, p
arXiv:2610.17907v1 Announce Type: cross Abstract: The code generation capabilities of large language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need to u
arXiv:2610.15417v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D)
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weight
arXiv:2610.14443v1 Announce Type: cross Abstract: Model cards, system cards, and safety reports increasingly document LLM safety behaviors, yet safety evaluations typically start from predefined bench
arXiv:2607.27964v3 Announce Type: replace-cross Abstract: Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies
arXiv:2610.19651v1 Announce Type: new Abstract: Hyperspectral imaging distinguishes RGB-similar objects, but a pretrained vision-language-action model needs a state its frozen decoder can use. SPECTRA
arXiv:2610.19232v1 Announce Type: new Abstract: Large language models impose substantial memory demands and arithmetic costs during inference. Dense-to-mixture-of-experts (MoE) conversion is a model o
arXiv:2502.11680v2 Announce Type: replace Abstract: We develop and evaluate a structure learning algorithm for clinical time series. Clinical time series are multivariate time series observed in multi
arXiv:2610.19520v1 Announce Type: new Abstract: Cameras and the foundation models built on them recognize what a 3D scene contains, but not what it is made of: surfaces of the same colour can be diffe
arXiv:2610.20303v1 Announce Type: new Abstract: Orthogonal transforms have emerged as an effective tool for low-bit quantization of large language models (LLMs), as they reshape activation distributio
arXiv:2610.20556v1 Announce Type: new Abstract: Interactive video generation commonly relies on small bidirectional chunks to reduce response latency. Yet our preliminary experiments show that larger
arXiv:2610.17689v1 Announce Type: new Abstract: Serverless inference is emerging as an efficient deployment model for Large Language Models (LLMs) due to its ability to elastically scale resources, im
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as pa
arXiv:2610.18438v1 Announce Type: cross Abstract: Molecular fragments provide chemically meaningful units, but existing molecular languages rarely make their locations and connections explicit for edi
arXiv:2610.17309v1 Announce Type: cross Abstract: We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-gu
Artificial intelligence governance startup nFOX Lab today launched a platform for managing owned large language models and announced plans to open-source Blockhouse, a security sandbox designed to res