Search: “agents”

arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, ex

arXiv:2610.07937v1 Announce Type: new Abstract: Redpine Science gives models and agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Pr

arXiv:2508.16821v2 Announce Type: replace Abstract: We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinfor

arXiv:2610.07781v1 Announce Type: new Abstract: Post-training quantization reduces the cost of deploying language-model agents, but its effect on recovery from temporary tool failures can depend on ho

Seems like a bit of a long shot, but since it’s so mystifying I figured I might as well ask: I have been trying to get Qwen 3.6 35B to function as a local implementation agent in my subagent driven de

arXiv:2610.08271v1 Announce Type: new Abstract: Classical reinforcement learning (RL) assumes that a reward is observed for every visited state-action pair. However, in real-world applications such as

arXiv:2610.07086v1 Announce Type: cross Abstract: LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool sch

arXiv:2610.07652v1 Announce Type: cross Abstract: The ability to interact with articulated objects is essential for embodied intelligent systems, but collecting large-scale real-world demonstrations f

AI is driving the biggest infrastructure build-out in history, with @Google alone forecasting $200B of capex in 2026E. What are the real constraints on a system at this scale? Amin Vahdat is the chief

GPU utilization during post-training depends partly on how efficiently infrastructure moves data and loads updated models. As enterprises continually refine AI agents, reducing delays between training

arXiv:2610.06204v1 Announce Type: cross Abstract: LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. S

arXiv:2610.04540v1 Announce Type: new Abstract: We introduce DreamFormer, a model-based agent that acquires language-conditioned, multi-task skills by imitating expert demonstrations within the latent

arXiv:2610.05013v1 Announce Type: new Abstract: Lifelong physical agents must reason over extended interactions where past events continue to shape the world long after they disappear from view. Beyon

arXiv:2610.05077v1 Announce Type: new Abstract: Backtests of LLM trading agents often assume that every order fills at the closing price. We ask whether this choice changes only reported returns or al

arXiv:2610.06153v1 Announce Type: new Abstract: Expressive humanoid interaction requires speech, facial animation, and body gestures to form a coherent response. However, many full-body humanoid robot

There's a party on Friday night that most of SF Tech Week will only hear about on Saturday. So, we made a vintage film to announce it. In the 1920s, inventions were rewriting everyday life and nobody

arXiv:2610.06432v1 Announce Type: cross Abstract: Numerous agentic workflows are based on a generator-verifier loop: a generator proposes candidates, a cheap verifier scores them, and the workflow ter

arXiv:2610.04911v1 Announce Type: cross Abstract: Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that releva

arXiv:2610.03102v1 Announce Type: cross Abstract: An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when th

arXiv:2610.02460v1 Announce Type: new Abstract: Recent benchmarks rely on user simulators to evaluate AI agents in multi-turn interaction. While existing simulation techniques demonstrate surface fide

arXiv:2610.03055v1 Announce Type: new Abstract: A coding agent can earn a passing grade by fixing its code, or by deleting the test that exposes the bug. Detecting such reward hacking requires recogni

arXiv:2610.03312v1 Announce Type: new Abstract: Background: We address the problem of planning when the set of feasible states or actions changes over time. For example, in the problem of path plannin

arXiv:2610.02413v1 Announce Type: new Abstract: LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hid

arXiv:2604.05088v2 Announce Type: replace-cross Abstract: We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulato

arXiv:2610.02417v1 Announce Type: new Abstract: Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic unde

if you’re building an ai app, you might want to host inference to improve your margins, and if you do that you should support a few models, and if you’re doing that you might as well build a router, a

arXiv:2610.01801v1 Announce Type: new Abstract: Can response safety be scored by cosine similarity to the mean embedding of known-safe responses? A recent sleeper-agent detector proposes exactly this

arXiv:2610.00859v1 Announce Type: new Abstract: World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video si

arXiv:2610.01999v1 Announce Type: new Abstract: Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities acc

arXiv:2610.01067v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) searching for ground targets from a high altitude face a unique challenge, particularly when the target is already withi

arXiv:2610.00314v1 Announce Type: new Abstract: Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while v

arXiv:2610.01780v1 Announce Type: new Abstract: A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the

This is beautiful work @huggingface! 🤗 The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guid

a lot of robot video data for thee We’re making the egocentric internet searchable. VideoDB now lets you search 12M+ task episodes from every open datasets. Type “arms folding a towel” and get thousan

arXiv:2609.39131v1 Announce Type: new Abstract: Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, m

arXiv:2609.39542v1 Announce Type: new Abstract: This report examines and compares some of the many fine tuning and prompting methods existing, applying them within the domain of autonomous driving. Th

arXiv:2609.39284v1 Announce Type: cross Abstract: While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning,

arXiv:2609.39601v1 Announce Type: cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fa

I built a free tool that lets your coding agent make videos like this one. You give your agent the link to the repo and say what the video should be about. It writes the words, draws the scenes, and y

arXiv:2609.40070v1 Announce Type: cross Abstract: When inference demand exceeds available compute capacity, model providers must decide which requests should be served first. Users have different tole

jes, a jev open-source guardrails project LangChain Ambassador @EdenEmarco177 has been working on It uses LangChain’s TypeSafeClassifier under the hood. The docs include a LangChain middleware example

arXiv:2609.39420v1 Announce Type: new Abstract: Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model

arXiv:2609.39976v1 Announce Type: cross Abstract: Mobile terminals need to provide application and network services while supporting users' control over their attention. We explore voice-first interac

A thing to know about the AI business is labs that have frontier models can release half-built products and they work surprisingly well because the AI can just figure stuff out and improvise. Its like

arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a maj

Google LLC today began rolling out Gemini 4 Argon, a frontier artificial intelligence model that beats rival models from Anthropic PBC and OpenAI Group PBC on most of Google’s benchmarks, to vetted cy