Knowledge catalogue
arXiv:2610.18878v1 Announce Type: new Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requi
arXiv:2610.20102v1 Announce Type: new Abstract: We investigate two aspects of multilingual pre-training with limited data, namely how language exposure is distributed across English, Dutch, and Chines
arXiv:2610.14552v1 Announce Type: cross Abstract: Protocol specifications rarely justify executable behavior in one place: a transition may inherit its source state from a remote control block, name i
arXiv:2610.19559v1 Announce Type: new Abstract: Lipreading remains challenging due to the inherent ambiguity of visual speech cues and their sensitivity to head pose and video resolution. In this work
arXiv:2610.18092v1 Announce Type: new Abstract: Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, e
arXiv:2610.18343v1 Announce Type: cross Abstract: Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of r
arXiv:2610.14615v1 Announce Type: cross Abstract: We study autoregressive token generation through the notion of sequential samplers: A circuit that samples the next symbol only given the previous one
arXiv:2610.20256v1 Announce Type: new Abstract: Long-horizon agents must coordinate reasoning, tool use, and environment feedback over extended interactions. Learning from sparse outcome rewards requi
arXiv:2607.08964v3 Announce Type: replace Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple
arXiv:2610.19138v1 Announce Type: cross Abstract: How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions und
arXiv:2610.20294v1 Announce Type: new Abstract: An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains. We propose MMLA-RSI, a recursive
arXiv:2610.19920v1 Announce Type: cross Abstract: Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of s
arXiv:2610.20459v1 Announce Type: new Abstract: Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grou
Nemotron-3.5-Embed-1B-BF16 is a versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval. The model can embed a document page in the form of an image,
arXiv:2610.18089v1 Announce Type: new Abstract: AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated eval
arXiv:2610.18784v2 Announce Type: new Abstract: Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved
arXiv:2503.21821v2 Announce Type: replace Abstract: We introduce Physics, a benchmark for evaluating foundation models on advanced physics problem solving. It contains 1034 annotated, open-ended probl
arXiv:2610.19131v1 Announce Type: cross Abstract: Maintenance work orders are the largest written record of how industrial equipment fails, yet in most plants they are close to unusable for analysis.
arXiv:2610.19011v1 Announce Type: new Abstract: The Practical Molecular Optimization (PMO) benchmark standardized evaluation in molecular optimization, but it is built on simple property-based oracles
arXiv:2610.16778v1 Announce Type: cross Abstract: Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII).
arXiv:2610.14912v1 Announce Type: new Abstract: Language models are increasingly used to create synthetic survey samples, also called silicon samples. Decision models are a new class of language model
arXiv:2606.18060v2 Announce Type: replace Abstract: As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Oth
arXiv:2601.08689v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong capabilities in finance-oriented question answering, yet their evaluation on professional quantitativ
arXiv:2610.19294v1 Announce Type: new Abstract: This work concerns our submission for the Multilingual track of the 2026 BabyLM Challenge. We improve on our baseline using data that has been summarize
arXiv:2610.19872v1 Announce Type: new Abstract: A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answ
arXiv:2610.14721v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones from a continuous unlabeled test stream after deployment. Existing TTD m
arXiv:2610.15884v1 Announce Type: new Abstract: False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this err
arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways. Revocation may be reported at issuer commit, transport acknowledgment, or receiv
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central saf
arXiv:2610.20221v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed across languages, yet their safety and reasoning capabilities remain predominantly evaluated in E
arXiv:2610.15056v1 Announce Type: cross Abstract: Large language models can post-edit ASR by using linguistic context to compare N-best hypotheses and rewrite the transcript when needed, often improvi
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: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:2610.17727v2 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:2610.17131v2 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:2610.19636v1 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:2610.17907v1 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:2610.19232v1 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:2603.09200v2 Announce Type: replace-cross Abstract: Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason st
arXiv:2610.14115v1 Announce Type: new Abstract: Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents tha
arXiv:2610.14736v1 Announce Type: new Abstract: Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. How
arXiv:2610.17324v1 Announce Type: cross Abstract: AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does
arXiv:2610.19725v1 Announce Type: new Abstract: Time-series foundation models provide strong zero-shot forecast, but deployment for real- world applications still requires task-specific designs for mo
arXiv:2610.19934v1 Announce Type: new Abstract: Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much
arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextu
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:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally r
arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model
arXiv:2610.14149v1 Announce Type: new Abstract: VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and ve
arXiv:2503.04940v3 Announce Type: replace-cross Abstract: Emergent Language (EL) focuses on the emergence of communication among artificial agents. Although symbolic communication channels more closel
We now have state-of-the-art pre-trained base models in the 3T-parameter weight class, built entirely in-house at MAI. Post-training results coming soon -- stay tuned! Lots of details in our technical
arXiv:2610.16927v1 Announce Type: new Abstract: Short-video search requires compact query rewriters that infer personalized intent from brief, ambiguous queries under strict latency constraints. The c
arXiv:2610.19476v1 Announce Type: cross Abstract: Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvemen
arXiv:2610.20052v1 Announce Type: new Abstract: Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a prop
arXiv:2610.20413v1 Announce Type: new Abstract: Momentum is a classical tool for accelerating convex optimization and a standard component of modern large language model training. Yet recent empirical
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:2610.17643v1 Announce Type: new Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmat
arXiv:2610.18420v1 Announce Type: cross Abstract: We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, ma