Knowledge catalogue
arXiv:2610.20785v1 Announce Type: new Abstract: Large language models are increasingly used in social interactions, where appropriate responses require recognizing implicit cues, inferring mental stat
arXiv:2502.13392v3 Announce Type: replace Abstract: Pioneering companies such as Waymo have deployed electric robo-taxi services in several U.S. cities. Operating such fleets requires coordinating rid
arXiv:2610.22067v1 Announce Type: new Abstract: Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. Ho
arXiv:2601.01982v2 Announce Type: replace Abstract: Large language models (LLMs) excel at natural language tasks but remain brittle in domains requiring precise logical and symbolic reasoning. Chaotic
arXiv:2610.21805v1 Announce Type: new Abstract: Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, materi
arXiv:2610.22160v1 Announce Type: cross Abstract: Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate contro
arXiv:2610.22295v1 Announce Type: new Abstract: Understanding characteristics and activities of individuals in complex multi-person environments is crucial for real-world applications. However, existi
arXiv:2610.22289v1 Announce Type: new Abstract: Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves
arXiv:2610.21789v1 Announce Type: cross Abstract: Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime catego
arXiv:2610.21125v1 Announce Type: new Abstract: Few-step generative models produce high-quality samples in one or a few evaluations. However, steering them toward desired properties remains difficult,
arXiv:2610.21342v1 Announce Type: new Abstract: The task of constructing a predictor that is simultaneously accurate under multiple evaluation metrics has been popularized recently under the name omni
arXiv:2610.20693v1 Announce Type: new Abstract: Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a con
arXiv:2610.21833v1 Announce Type: new Abstract: Grid foundation models (GridFMs) are graph transformers pretrained on a masked power-flow objective, and evaluate power flow orders of magnitude faster
arXiv:2610.20973v1 Announce Type: new Abstract: Geo-foundation models (GFMs) are typically evaluated by downstream task predictive performance, revealing little about which physical features they are
arXiv:2610.22041v1 Announce Type: new Abstract: World-model planners evaluate candidate trajectories by predicting their future consequences, implicitly relying on the plan-to-motion relationship lear
arXiv:2610.21614v1 Announce Type: cross Abstract: Large audio language models (LALMs) have made substantial progress in audio understanding. However, in high-throughput applications requiring frequent
arXiv:2610.20766v1 Announce Type: new Abstract: Imagined speech decoding from EEG offers a promising route toward naturalistic brain-computer interfaces. Traditional closed-set classifiers treat seman
arXiv:2610.21188v1 Announce Type: new Abstract: Faulty sensor readings can distort estimates of fuel use and carbon dioxide emissions from diesel engines. We evaluate two procedures that use relations
arXiv:2610.21113v1 Announce Type: cross Abstract: Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LL
arXiv:2610.21253v1 Announce Type: cross Abstract: Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements urging users who disclose suicide thoughts to
arXiv:2610.21555v1 Announce Type: cross Abstract: Muon's gains in data efficiency motivate evaluating its performance under explicit data, time, and tuning budgets. On a single A100 GPU, we compare a
arXiv:2610.15788v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent,
arXiv:2604.25083v2 Announce Type: replace Abstract: Computer Architecture research has traditionally required the exploration of vast, highly complex design spaces through manual human effort. Large L
arXiv:2610.17206v1 Announce Type: new Abstract: We propose AutoMARS (Automatic Multi-Agent Risk Assessment), an agentic framework for automatic and scalable comparative risk assessment in supply chain
arXiv:2610.20514v1 Announce Type: new Abstract: Evaluations of classifiers (AI or human or agents) often assume a batch setting in which every agent produces labels on every example in a test set, whi
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribu
arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users i
arXiv:2610.15008v1 Announce Type: new Abstract: Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policie
arXiv:2610.20293v1 Announce Type: cross Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulti
arXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An a
arXiv:2610.18415v1 Announce Type: cross Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment ste
arXiv:2610.19523v1 Announce Type: new Abstract: Robotic exploration, coverage, and multi-agent deployment algorithms require reproducible environments with controllable geometry and visibility. This p
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily e
arXiv:2610.20396v1 Announce Type: new Abstract: When does a human correction become useful learning, and what establishes better segmentation at matched human effort? This critical narrative review fo
arXiv:2610.19427v1 Announce Type: new Abstract: Legal reasoning is a fundamental capability for large language models (LLMs) to complete legal AI tasks such as legal judgment prediction. In legal prac
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:2604.03414v2 Announce Type: replace Abstract: Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the lar
arXiv:2610.19571v1 Announce Type: new Abstract: Real-world engineering drawings are often large-format and information-dense. Answering practical engineering questions therefore requires both fine-gra
arXiv:2610.18522v1 Announce Type: new Abstract: Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We tes
arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valida
arXiv:2610.19659v1 Announce Type: new Abstract: People delegate multi-step work to LLM agents and read only the reply that the agent hands back. Current evaluation scores task completion and the faith
arXiv:2610.20172v1 Announce Type: cross Abstract: Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel w
arXiv:2610.18612v1 Announce Type: cross Abstract: System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly driv
arXiv:2412.12877v3 Announce Type: replace Abstract: Recent Artificial Intelligence (AI)-based video editing has enabled users to edit videos through simple text prompts, significantly simplifying the
arXiv:2610.20004v1 Announce Type: new Abstract: Transformers can perform in-context reinforcement learning without parameter updates. However, existing theoretical constructions often require context
arXiv:2610.16133v1 Announce Type: cross Abstract: Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require mu
arXiv:2610.19765v1 Announce Type: new Abstract: Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. I
arXiv:2610.03966v2 Announce Type: replace Abstract: Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, mak
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:2601.07239v2 Announce Type: replace Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As la
arXiv:2610.19102v1 Announce Type: new Abstract: Aerial and remote sensing video is increasingly evaluated like web video, by posing multiple-choice questions to multimodal large language models (MLLMs
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
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:2605.06068v2 Announce Type: replace Abstract: For years, we have built LLM serving systems like any other critical infrastructure, with a single general-purpose stack hand-tuned over many engine
arXiv:2610.19910v1 Announce Type: new Abstract: Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rul
arXiv:2610.19583v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly used to generate text, their misuse has become a growing societal problem, with implications for acad
arXiv:2605.05662v2 Announce Type: replace-cross Abstract: Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. More
arXiv:2610.15666v1 Announce Type: new Abstract: Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interac
arXiv:2610.16012v1 Announce Type: cross Abstract: Autonomous driving (AD) relies on multi-sensor perception to interpret the surrounding environment. However, the robustness of camera--radar fusion un