Search: “reasoning”

arXiv:2609.38641v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize know

arXiv:2609.40031v1 Announce Type: cross Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated con

arXiv:2609.38232v1 Announce Type: cross Abstract: Streaming spoken agents may take an external action before the available speech supports it, yet final-turn scores do not reveal whether each observed

arXiv:2609.38262v1 Announce Type: cross Abstract: Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records.

40 year tech gap? No problem! The Tandy runs DeskMind, a native DOS program. It talks over WiFi (a PicoMEM 2 card with mTCP) to a small Python server on my PC. That server drives Qwen3.8-27B (NInfer o

arXiv:2609.25187v2 Announce Type: replace Abstract: Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems

arXiv:2609.36058v1 Announce Type: new Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods

arXiv:2607.11849v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on high-school and competition-level mathematics, yet their capabilities on advanc

arXiv:2609.35886v1 Announce Type: cross Abstract: AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a co

arXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cover

arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an imp

arXiv:2609.37027v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT), yet a performance gap can remain relative to full fine-t

arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by

arXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont

arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabora

arXiv:2609.36931v1 Announce Type: new Abstract: Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked f

arXiv:2502.04492v3 Announce Type: replace Abstract: The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive framewo

arXiv:2609.36455v1 Announce Type: new Abstract: Large language models are thought to represent features by vectors in a hidden space of dimension given by the model's width. Superposition, in which mo

arXiv:2609.37810v1 Announce Type: cross Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains chall

arXiv:2506.11261v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have shown promising progress in robotic manipulation. However, directly mapping visual observations and l

Half a million downloads in a month. Today, our open source family takes another step forward. Thank you for the incredible support behind our first-generation models. We’re excited to introduce TwIL-

arXiv:2609.36546v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student model on its self-generated trajectories with dense token-level teacher feedback. However, naive OPD may

arXiv:2609.37170v1 Announce Type: cross Abstract: Off-policy and on-policy distillation have traditionally been formulated as separate paradigms, each favoring a different property of distillation tra

arXiv:2609.35868v1 Announce Type: new Abstract: Is human readability necessary for effective fine-tuning of large language models? We investigate whether model-conditioned training representations can

arXiv:2609.37891v1 Announce Type: new Abstract: Current pre-training datasets are derived from web crawls, with all their issues, and were not designed to support mid- and post-training pipelines--for

arXiv:2609.36246v1 Announce Type: new Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressively

arXiv:2609.35793v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR). An exact verifier can also support tes

arXiv:2609.37834v1 Announce Type: new Abstract: Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes th

arXiv:2609.37209v1 Announce Type: new Abstract: Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairwi

arXiv:2609.37712v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, local

arXiv:2609.36642v1 Announce Type: new Abstract: Language-model agents are usually trained by reinforcement learning from one reward per episode, and privileged self-distillation enriches it by letting

arXiv:2609.38018v1 Announce Type: new Abstract: Group relative policy optimization (GRPO) learns only from prompts whose sampled responses disagree: a group that is entirely correct or entirely incorr

arXiv:2609.37311v1 Announce Type: new Abstract: Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative age

arXiv:2609.36850v1 Announce Type: new Abstract: Generative content is increasingly entering the production and dissemination of news, transforming fake news from manually fabricated or simply manipula

arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template

arXiv:2609.37666v1 Announce Type: cross Abstract: Search and Rescue (SAR) operations increasingly deploy heterogeneous teams of aerial and ground robots. However, conventional coverage methods typical

arXiv:2609.36742v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for improving large language models (LLMs) on various tasks, yet it

arXiv:2609.36171v1 Announce Type: new Abstract: Large-scale demonstrations have driven unprecedented progress in robot learning, yet collecting robot data through teleoperation is expensive and diffic

arXiv:2609.36562v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal imp

Timelines just got shorter... AI will understand the physical 3D space better than humans by November* Is Google so back? Their new Gemini 4 Argon understands the physical 3D world better than any oth

arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wit

I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy

arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation

arXiv:2609.35521v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informati

arXiv:2609.35193v1 Announce Type: new Abstract: Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supportin

arXiv:2609.32932v1 Announce Type: new Abstract: Finite computational resources force a tradeoff between automatic System 1 processes and costly System 2 thinking. Large language models (LLMs) can spen