Does self-distillation improve reasoning?
arXiv:2610.18613v1 Announce Type: new Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct
Knowledge catalogue
arXiv:2610.18613v1 Announce Type: new Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct
arXiv:2610.18862v1 Announce Type: cross Abstract: Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more tokens than needed to solve a problem. Existing
arXiv:2610.18861v1 Announce Type: cross Abstract: How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and
Introducing the largest open-source multilingual, multimodal RL environments 🌍 📄 OCR: 1M+ document pages in 22 languages 🎙️ ASR: speech in 102 languages 12M+ tasks across two OpenEnv Environments, ope
arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains
arXiv:2503.07775v3 Announce Type: replace Abstract: Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples i
arXiv:2610.18868v1 Announce Type: cross Abstract: Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a cap
arXiv:2610.15570v1 Announce Type: cross Abstract: Settling one comparison between two truncation samplers has cost six thousand A100-hours, and nothing says in advance how far apart two samplers can b
🚨 @AnthropicAI: AI “MAY BE” capable of self-replicating! Now read the actual research: • No fully autonomous rogue replicator demonstrated. • Cyber exploitation deliberately simplified. • Real-world r
(1/7) I'd like to provide some additional context for the remarks that can be found in this interview. (2/7) My discomfort with the attention being paid to existential risk---and with the ongoing domi
arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme
arXiv:2610.13057v1 Announce Type: cross Abstract: Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by th
arXiv:2610.12776v1 Announce Type: new Abstract: Automatic differentiation (AD) is a cornerstone of modern machine learning. Since all AD frameworks implicitly fix a basis of Euclidean space to define
arXiv:2610.13116v1 Announce Type: new Abstract: As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce s
arXiv:2610.13430v1 Announce Type: cross Abstract: Time series causal discovery --- the process of detecting causation between time series --- has its roots in signal processing research from over a ha
arXiv:2610.13225v1 Announce Type: cross Abstract: Generative modeling for discrete data has been significantly advanced by learning continuous vector fields on the statistical manifolds to transport s
arXiv:2610.13912v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model
Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap
What does the world look like inside an AI model? Here are 3 world model architectures based on how they represent the world (+ the subtypes) ↓ 1. A generated observation – a model predicts what comes
arXiv:2604.05716v2 Announce Type: replace Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an
arXiv:2610.11410v1 Announce Type: new Abstract: Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large multimodal models. Yet affective sci
arXiv:2610.12023v1 Announce Type: new Abstract: Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like market research, public polling, preference elicit
arXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this scree
arXiv:2603.07980v2 Announce Type: replace-cross Abstract: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks
arXiv:2610.11529v1 Announce Type: new Abstract: Self-distillation can improve reasoning without a separately trained, more capable teacher, but its effectiveness depends on how the self-teacher gains
BREAKING: President Trump on Elon Musk today: “First, we honor an industrial titan, a brilliant engineer, and one of the greatest technology founders to ever live. His name is Elon Musk. Quite honestl
arXiv:2610.09769v1 Announce Type: cross Abstract: Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental impr
I find it odd watching armchair critics rush to nitpick @MistralAI’s plans or obsess over whether they’re #1 on every leaderboard. Having a team with this level of conviction building frontier models
In recent decades, Ireland has grown into a vibrant hub for global technology. As modernization accelerates, Irish organizations — spanning government agencies, established enterprise brands, and grow
arXiv:2610.10513v1 Announce Type: cross Abstract: Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer,
arXiv:2610.05685v2 Announce Type: replace Abstract: Reasoning models write most of their KV cache while decoding long chains of thought (CoT), so the cache has to be compressed online under a fixed me
🧬 Training and evaluating AI scientists on drug target discovery is hard. We introduce DrugTargetWorld: Synthetic Biomedical Worlds for Training and Benchmarking AI Scientists The environment turns en
arXiv:2610.08680v1 Announce Type: cross Abstract: Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-speci
arXiv:2610.07019v1 Announce Type: new Abstract: Fiorillo v0.5 is an open model that answers typed questions with a probability for each answer. Its main specialist reads a randomized trial's article,
arXiv:2610.07620v1 Announce Type: new Abstract: Scientific law discovery requires selecting measurements and converting evidence into a governing equation. We evaluate an explore-then-commit protocol
arXiv:2610.05275v2 Announce Type: replace Abstract: A large part of political discourse on social media is built and expressed at a level of claims: i.e. declarative, typically single-clause statement
arXiv:2610.07184v1 Announce Type: cross Abstract: A key challenge in building AI systems for scientific research is enabling extit{scientific exploration}: the systematic process of investigating unkn
arXiv:2610.07226v1 Announce Type: cross Abstract: ``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation a
arXiv:2610.08699v1 Announce Type: new Abstract: Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, wit
arXiv:2512.03579v2 Announce Type: replace Abstract: Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating
arXiv:2610.07851v1 Announce Type: new Abstract: Agentic workflows enable large language models (LLMs) to solve complex tasks by coordinating reasoning, tool use, and verification. However, a workflow
arXiv:2610.07625v1 Announce Type: cross Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay
arXiv:2610.06824v2 Announce Type: replace Abstract: We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick i
arXiv:2610.04343v1 Announce Type: cross Abstract: Reservoir computing (RC) is a machine learning technique for data-driven modeling of dynamics for forecasting and control, primarily studied in comput
arXiv:2610.05863v1 Announce Type: new Abstract: High-quality child care in early life is a critical determinant of children's growth and development. Research on child care quality has been constraine
arXiv:2610.04499v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to convert medical images into diagnostic texts to assist in clinical decision-making and alleviate the workload
arXiv:2610.06580v1 Announce Type: new Abstract: Spike-and-slab regression is a standard Bayesian formulation of variable selection: it returns a posterior distribution over which candidate effects are
arXiv:2610.04419v1 Announce Type: new Abstract: Generative models are often trained with isotropic objectives such as mean-squared error. For data concentrated near a low-dimensional manifold, however
arXiv:2603.09693v2 Announce Type: replace Abstract: Predicting interfacial degradation and microstructural evolution through phase-field modelling is computationally intensive, particularly for parame
arXiv:2610.02972v1 Announce Type: new Abstract: Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability model to every candidate and criterion is costly.
arXiv:2610.03524v1 Announce Type: new Abstract: General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and col
arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation do
arXiv:2610.02515v1 Announce Type: cross Abstract: We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade
arXiv:2610.03631v1 Announce Type: new Abstract: Designing a scientific instrument tests whether language-model agents can do physics rather than recall it, provided the grading cannot be argued with.
arXiv:2610.02510v1 Announce Type: new Abstract: Campus AI tutors based on retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dial
arXiv:2610.02588v1 Announce Type: new Abstract: Agents are increasingly given open-ended research tasks: discovering an empirical law from self-designed experiments, improving a heuristic whose optimu
arXiv:2610.03548v1 Announce Type: new Abstract: Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recurs
arXiv:2610.02975v1 Announce Type: new Abstract: Large language model (LLM)-based self-evolving search is a promising approach to scientific discovery. However, high-fidelity evaluation of every candid
arXiv:2610.03525v1 Announce Type: new Abstract: Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential
arXiv:2610.02417v1 Announce Type: new Abstract: Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic unde