Explore tools, prompts, skills, news and resources related to arXiv 第10页.
Latest articles, prompts, use cases and editorial content about arXiv 第10页
Researchers introduce a framework for evaluating whether LLM agents can find inactive conversations, autonomously return to them and reconstruct enough context for coherent continuation. Across six LLM configurations, co...
Researchers propose an LSTM-based variational autoencoder to generate training sequences representing under-observed transitions toward unstable anaerobic digestion operations. Using one year of full-scale plant data, th...
PAPERBENCHX introduces 93 expert-constructed paper-reproduction tasks across 12 research areas, covering disciplines including chemistry, biology, photonics and robotics. Evaluation replays submissions from scratch and s...
Edge0 released Audio8-TTS-Realistic, a 601M-parameter text-to-speech model supporting 23 languages and zero-shot voice cloning from a reference clip and transcript, with weights and code under Apache 2.0. Its training us...
Anthropic hiring manager Felix Rieseberg announces the end of traditional coding interviews, advising junior engineers to focus on business impact and rapid prototyping. Google DeepMind launches Genie 4, a real-time worl...
Elorian launched Glimpse, its first visual reasoning model, and co-released the DecoyCount benchmark with Mercor to test whether models genuinely count objects or rely on shortcuts. Frontier models scored below 50% accur...
AWS announced that NVIDIA Nemotron 3.5 Super VL, a 120B-parameter MoE multimodal model, is now available on AWS and detailed its deployment on Amazon EKS, EKS Auto Mode, and SageMaker HyperPod EKS. The model activates 12...
KPPax is a kinetic preprocessor that turns mechanisms written in the Kinetic PreProcessor (KPP) language into differentiable, just-in-time compiled, and vectorisable chemistry code in JAX. It evaluates rate laws with spa...
Researchers define a temporal variability score (TVS) as the coefficient of variation of an item’s negative log-likelihood across point-in-time language models trained on web snapshots from different years. Using six ben...
The paper introduces CrossProfile, a diagnostic benchmark of 60 templates and 480 tasks with verified answer keys that crosses ownership of supporting, decoy, and irrelevant facts while holding their text fixed. On Qwen2...
Timestral is a family of four probabilistic time series foundation models with 5M, 28M, 123M, and 209M parameters. The design uses Decoupled Horizon Forecasting to separate prediction tokens from causally encoded context...
Researchers introduced TeamGym, an environment for evaluating and training language-model agents on team decision-making tasks built from legal, finance, medical, and software engineering corpora. TeamGym uses a method t...
A new arXiv paper introduces Task Advancement Memory (TAM), which treats verified task progress as both execution state and supervision for GUI agents. Task Advancement State tracks how verified progress changes remainin...
Concordat is an open-source Python library that treats an LLM agent as a finite-state protocol in the spirit of typestate and session types, and enforces that protocol at runtime. Each turn offers only tools legal in the...
Researchers introduced M4Bench, a benchmark of 28 clinical derivation tasks across 15 task families using MIMIC-IV and eICU, to test whether AI coding agents can reproduce EHR-derived variables and how clinician-reviewed...
This arXiv study uses causal interventions to test whether Gemma4-12B-it uses a shared internal numerical representation for text and image inputs and for addition and subtraction. It learns subspaces in the residual str...
FoG is a framework for training knowledge-graph agents to retrieve the supporting triples behind factual answers, not merely produce correct answers. It combines evidence-grounded synthesis that hides explicit entities b...
Agent-Conditioned Routing (ACR) runs parallel trajectories inside one frozen sparse mixture-of-experts model by applying persistent, untrained shared and private expert-eligibility masks while keeping the learned, input-...
A new white-box framework, CauTrace, analyzes why LLMs fail by tracking seven functional states for support and constraint processing, how representation changes propagate across Transformer blocks, and the timing and to...
The paper proposes a formal framework for analyzing whether responsibilities in multi-agent systems align with agents' operational ability to fulfil them. It discusses design dimensions for describing normatively re...
