Search: “tools”

arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has

arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph pr

arXiv:2602.01709v3 Announce Type: replace Abstract: Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, ye

arXiv:2610.13862v1 Announce Type: new Abstract: Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-

arXiv:2610.13025v1 Announce Type: new Abstract: Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improve

arXiv:2610.12793v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because

arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes

I've been investigating some serious ChatGPT reliability issues over the past several days, and my latest tests revealed something particularly interesting: Both GPT-5.6 and GPT-6 showed problems unde

Agents are only as capable as the context they can reach. An agent with reliable access to the right information makes decisions grounded in fact; one without it guesses. And the work agents produce i

arXiv:2610.12518v1 Announce Type: cross Abstract: This position paper argues that the generative molecular dynamics (GenMD) community is not properly evaluating its progress: current evaluations let a

arXiv:2610.13829v1 Announce Type: cross Abstract: A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one

arXiv:2610.12963v1 Announce Type: cross Abstract: Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Bey

Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure mode

arXiv:2610.13790v1 Announce Type: cross Abstract: How well can vision-language models (VLMs) reason about what is missing from an image? We study this question with OccludeBench, a manually curated be

Over the last few months at @river_ai_inc we’ve developed what we believe is the best system in the world for building your own internal custom models, driven by 10 years of experience training top mo

EXL3-QLoRA I've built this over the last few months and I think it's stable enough to share now. A fork of ExLlamaV3, this is a native ExLlamaV3 training implementation with plain PyTorch, without tra

arXiv:2610.13152v1 Announce Type: new Abstract: Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. Ho

arXiv:2610.13438v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and to

arXiv:2610.13527v1 Announce Type: cross Abstract: Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly underst

arXiv:2610.13207v1 Announce Type: new Abstract: Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive pattern

arXiv:2610.12975v1 Announce Type: new Abstract: We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents agains

arXiv:2610.13835v1 Announce Type: new Abstract: An ideal (language) model must continually update its knowledge. Existing work largely focuses on making these updates efficient after training. We inve

arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short a

arXiv:2610.13461v1 Announce Type: new Abstract: AI systems are making rapid progress in mathematics, but this progress is hard to measure. Benchmarks of solved problems saturate, and in benchmarks of

Brock E.W. Turner / Axios: Suki, an AI ambient scribe for healthcare providers, raised a 90M Series E led by Healthier Capital; a source says it projects 60M-80M in revenue this year — Suki, a health

arXiv:2610.13356v1 Announce Type: new Abstract: Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success c

arXiv:2610.12828v1 Announce Type: new Abstract: Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and un

arXiv:2412.06534v5 Announce Type: replace-cross Abstract: Understanding the internal mechanisms of deep neural networks remains a central challenge in machine learning. In computer vision, one promisi

arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su

arXiv:2610.12832v1 Announce Type: new Abstract: Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key cha

At NetApp INSIGHT 2026, Vultr highlighted the emerging “beyond hyperscale” era of enterprise infrastructure, emphasizing that agentic AI and modernized applications require more than compute and stora

arXiv:2603.17917v2 Announce Type: replace-cross Abstract: Large language models (LLMs) contain billions of parameters, but many exact weight values are not essential. We apply scalar K-means clusterin

Financial institutions are adopting artificial intelligence faster than many compliance teams can establish the controls needed to oversee it. That gap is raising new questions about AI-powered compli

arXiv:2610.12876v1 Announce Type: cross Abstract: Mixed-integer programming (MIP) solvers are widely used, yet their performance can vary substantially even under seemingly neutral perturbations. Such

No more excuses for GPU-poor folks not to start LLMing! Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) ~9.3x smaller than FP16 (ideal) | 98.2% of FP16 intell

AI solved open mathematical problems. But the biggest surprise came afterwards. A team at Google DeepMind has used AI to resolve 9 open Erdős problems, including questions that had remained unsolved f

Running HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Q4_K_M with llama.cpp at ~600 tok/s prefill and 23 tok/s decode, 131k context window, Q8 KV cache - on an RTX 2060 6GB + 32GB DDR4 RAM.

arXiv:2610.12465v1 Announce Type: cross Abstract: General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (R

arXiv:2610.10607v1 Announce Type: new Abstract: Immersive VR180 video is increasingly produced with professional stereo fisheye cameras, yet public VR180 research resources are mostly collected from o

arXiv:2610.11054v1 Announce Type: new Abstract: Soft pneumatic actuators are widely used in soft robotics. However, their actuation modes are typically fixed by internal chamber designs or reinforceme

arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for eva

arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settin

arXiv:2610.10946v1 Announce Type: new Abstract: Large language models (LLMs) are entering wildfire management, where overstated evaluations can cost property and lives. How do they perform on wildfire

arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality an

I made BigMoeOnEdge+ (BigMoeOnEdge-plus), a fork of Helldez's BigMoeOnEdge, the engine that streams MoE experts from flash so models bigger than RAM can run on-device. It adds a full Android chat app

Bullish on this trend of making post-training more accessible. A new post-training era is upon us. If you work on agentic RL, long-context tasks (a big focus today) are expensive, inefficient, and don