Knowledge catalogue
arXiv:2610.15150v1 Announce Type: new Abstract: Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback.
arXiv:2610.18230v1 Announce Type: cross Abstract: While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused
arXiv:2504.01627v2 Announce Type: replace-cross Abstract: Introduction: Horizon scanning in healthcare assesses early signals of innovation, crucial for timely adoption. Current horizon scanning faces
Editor's note: Generative AI startups are moving rapidly beyond static clip generation to build interactive, real-time worlds. In this technical deep dive, we explore how AI startup Visko collaborated
arXiv:2610.19686v1 Announce Type: new Abstract: Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed
arXiv:2610.18497v1 Announce Type: new Abstract: Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no referenc
arXiv:2610.15081v1 Announce Type: new Abstract: Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying gene
arXiv:2610.18950v1 Announce Type: cross Abstract: Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot demonstrations at scale remains c
arXiv:2610.20585v1 Announce Type: cross Abstract: Current approaches for steady partial differential equations surrogate models on unstructured meshes apply a single mixing mechanism to the whole solu
arXiv:2610.17928v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a
arXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging bec
arXiv:2610.17763v1 Announce Type: new Abstract: Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and
arXiv:2610.19728v1 Announce Type: cross Abstract: Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these halluci
arXiv:2610.15282v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource socioling
arXiv:2610.16027v1 Announce Type: cross Abstract: Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed err
arXiv:2610.19027v1 Announce Type: cross Abstract: Chance-constrained stochastic programs (CCSPs) require solutions that satisfy uncertain constraints with high probability. Standard approaches either
arXiv:2610.15208v1 Announce Type: cross Abstract: Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. A
arXiv:2610.19314v1 Announce Type: new Abstract: Large language model (LLM) evaluators are increasingly used to assess personalized assistants, yet whether they can reliably judge personalization has r
arXiv:2603.23678v2 Announce Type: replace Abstract: Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy const
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history
arXiv:2610.19372v1 Announce Type: new Abstract: Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded
arXiv:2409.00696v4 Announce Type: replace-cross Abstract: Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs).
arXiv:2610.14659v1 Announce Type: new Abstract: Streaming speech assistants can launch tools before users finish speaking, overlapping execution with incoming speech to reduce user waiting time. Howev
arXiv:2610.20503v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by drafting multiple tokens per step, yet feature-based drafters rely on target hidden featur
arXiv:2610.19044v1 Announce Type: cross Abstract: Tiny robots have limited computation and memory, yet visual navigation systems often maintain more state than a task requires. We ask whether persiste
arXiv:2610.19495v1 Announce Type: cross Abstract: Retrieving useful context for a robot requires matching its task, execution stage, and the continuation that should follow. We introduce Robota-Embed,
arXiv:2610.19931v1 Announce Type: new Abstract: Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tr
arXiv:2610.17820v1 Announce Type: cross Abstract: TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns
arXiv:2610.20457v1 Announce Type: new Abstract: Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences. Natural-language scientific claims, wri
arXiv:2603.07373v2 Announce Type: replace-cross Abstract: The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed inter
arXiv:2610.19394v1 Announce Type: new Abstract: Next-location prediction can support proactive mobile-network decisions, but acting on unreliable predictions can waste resources. We apply MetaModelSel
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:2610.16814v1 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:2610.19484v1 Announce Type: cross Abstract: Sequential conformal prediction needs to decide which past errors should calibrate uncertainty for the current target. Recency and online error feedba
arXiv:2602.22583v2 Announce Type: replace Abstract: Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems
arXiv:2610.18004v1 Announce Type: cross Abstract: Coding agents use generated tests to decide whether a proposed patch satisfies an issue's requirements. A suite that fails on the buggy program and pa
arXiv:2610.18216v1 Announce Type: cross Abstract: LLM agents can adapt to task feedback by revising the textual context that guides their behavior, without changing their model parameters. However, tu
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Blog: https://pub.sakana.ai/agentic-scientist/ GitHub: https://github.com/SakanaAI/AI-Scientist-v3 arXiv: htt
arXiv:2610.19369v1 Announce Type: new Abstract: Pedestrian tracking in video is important for applications such as surveillance and scene analysis, but it becomes more challenging in crowded scenarios
arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen res
arXiv:2610.14776v1 Announce Type: cross Abstract: Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity. However, neither objective captures the prosodic
arXiv:2610.19316v1 Announce Type: cross Abstract: Assigning routine tasks to cheaper large language model (LLM) providers can reduce generation cost, but switching providers may require processing acc
arXiv:2610.16155v1 Announce Type: new Abstract: Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking
arXiv:2609.31937v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing ea
arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how i
arXiv:2610.18949v1 Announce Type: cross Abstract: Existing machine-learning models for perovskite solar cells struggle to predict devices made from new materials. Most treat device layers as arbitrary
arXiv:2610.14360v1 Announce Type: new Abstract: Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many c
arXiv:2610.19052v1 Announce Type: new Abstract: Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable
arXiv:2610.14238v1 Announce Type: cross Abstract: LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a nat
arXiv:2610.14603v1 Announce Type: new Abstract: Due to the high cost of hardware experiments, robot policies are predominantly evaluated by comparing their empirical performance on a limited number of
arXiv:2610.18097v1 Announce Type: new Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training
arXiv:2610.16048v1 Announce Type: new Abstract: Backward conformal prediction (BCP) fixes the size of a prediction set and estimates its miscoverage, but assumes calibration and test data are exchange
arXiv:2610.16147v1 Announce Type: new Abstract: Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensi
arXiv:2610.15330v1 Announce Type: new Abstract: Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation i
arXiv:2610.14598v1 Announce Type: new Abstract: The effective integration of features derived from RGB images and 3D point clouds presents a substantial challenge in the field of multimodal anomaly de
arXiv:2610.17356v1 Announce Type: new Abstract: Driving digital head avatars is classically done by hand-crafted artist design or by image-based facial performance capture. In this work, we ask whethe
arXiv:2602.04692v3 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems
arXiv:2610.14630v1 Announce Type: new Abstract: Dual-lens super-resolution (DuSR) aims to enhance a wide-angle low-resolution (LR) image by exploiting a telephoto reference (Ref) image. A central chal
arXiv:2610.17718v1 Announce Type: cross Abstract: Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a re