Search: “reasoning”

'Strawberry' was OpenAI's internal code word for the extended reasoning capabilities featured in the o1-preview model, which enables the AI to work through complex problems with longer chains of thoug

arXiv:2601.23224v2 Announce Type: replace Abstract: Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting th

arXiv:2605.20743v1 Announce Type: cross Abstract: Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expresse

arXiv:2605.20194v1 Announce Type: new Abstract: Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when ana

arXiv:2605.21130v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have shown promise for video quality assessment, but most methods still predict an absolute score for each video. Such po

arXiv:2605.18891v1 Announce Type: cross Abstract: Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace kee

arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on

arXiv:2605.19352v1 Announce Type: cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the

arXiv:2605.19995v1 Announce Type: new Abstract: Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, le

An OpenAI general-purpose reasoning model autonomously disproved a conjecture posed by Paul Erdos in 1946, overturning 80 years of mathematical belief. The breakthrough concerns the planar unit distan

arXiv:2605.19173v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored for clinical decision support, yet most evaluations are conducted in English, leaving their relia

arXiv:2605.20158v1 Announce Type: cross Abstract: Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raise

The proof came from a general-purpose reasoning model, not a system built specifically to solve math problems or this problem in particular, and represents an important milestone for the math and AI c

This result points to something larger: AI systems are becoming capable of holding together long, difficult chains of reasoning, connecting ideas across distant fields, and surfacing paths researchers

arXiv:2511.06316v3 Announce Type: replace Abstract: In low- and middle-income countries, public safety and urban planning initiatives frequently face a critical shortage of accurate, location-specific

arXiv:2601.08679v3 Announce Type: replace Abstract: As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can

arXiv:2605.18352v1 Announce Type: new Abstract: Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models.

arXiv:2605.16568v1 Announce Type: new Abstract: Knowledge Graphs are pivotal for semantic data integration. The real-world data they model is often inherently uncertain. Within knowledge graphs, uncer

arXiv:2605.17497v1 Announce Type: new Abstract: GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We

arXiv:2605.18109v1 Announce Type: new Abstract: In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean

Reasoning is becoming commoditized. The uniqueness of your knowledge is your real advantage. Check out our Head of Developer Relations @RoieSchwabco on @TheEntAIShow with @bgracely: 📺 https://www.yout

arXiv:2509.21465v3 Announce Type: replace Abstract: Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by p

arXiv:2505.15692v5 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rel

There are a lot of coding and reasoning benchmarks for AI agents, but not a lot for document understanding - which is a prerequisite for all downstream knowledge work. We released ParseBench ~a month

1/3 My time at Meta FAIR will soon come to a close. I joined nearly two years ago full-time to help advance LLM reasoning. It has been a remarkable journey working with and leading an exceptionally ta

arXiv:2605.14344v1 Announce Type: new Abstract: Generative modeling has emerged as a promising approach for crystal structure discovery. However, existing LLM-based generative models struggle with low

arXiv:2605.14036v1 Announce Type: new Abstract: In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, ther

arXiv:2605.14696v1 Announce Type: new Abstract: Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving rel

arXiv:2605.15171v1 Announce Type: cross Abstract: Disease screening is critical for early detection and timely intervention in clinical practice. However, most current screening models for medical ima

arXiv:2605.06132v2 Announce Type: replace Abstract: In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the 're

arXiv:2605.15153v1 Announce Type: cross Abstract: We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a sing

arXiv:2605.15044v1 Announce Type: cross Abstract: As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-L

arXiv:2605.14876v1 Announce Type: cross Abstract: Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex s

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement.

arXiv:2605.14754v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowle

Yann LeCun says LLMs are strongest in domains where language itself is the substrate of reasoning, like math and code They can solve problems, prove theorems, and write programs — but they are not cre

arXiv:2605.13687v1 Announce Type: cross Abstract: We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context

arXiv:2605.12532v1 Announce Type: cross Abstract: Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the seman

arXiv:2605.13255v1 Announce Type: new Abstract: On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provid

arXiv:2602.07458v4 Announce Type: replace Abstract: Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and

arXiv:2605.12227v1 Announce Type: new Abstract: Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. E

Do multi-agent systems make LLM reasoning better? Most AI devs assume that it should. But this new paper shows that this is often not the case. It ran 22,500 deterministic trajectories across GAIA, SW

One of the biggest challenges with agents is that they produce way more than just tokens. Tool calls. State updates. Intermediate reasoning. Subagent progress. File changes. Custom events. Structured

arXiv:2605.09678v1 Announce Type: new Abstract: While extremely powerful and versatile at various tasks, the thinking capabilities of large language models (LLMs) are often put under scrutiny as they

arXiv:2605.09159v1 Announce Type: new Abstract: Recent work shows that large language models (LLMs) encode behavioural traits ('personas') as linear directions in activation space, often called 'perso

arXiv:2605.08695v1 Announce Type: new Abstract: Forensic analysis of AI-edited images requires more than binary real-versus-fake prediction: a useful system should localize the edit, identify its sema