Search: “agents”

arXiv:2606.27233v1 Announce Type: cross Abstract: We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis on the emerging dynamics of human

At this week’s TM Forum DTW Ignite conference in Copenhagen, industry leaders gathered to evaluate how agentic AI — the autonomous artificial intelligence systems capable of executing complex workflow

excited to come down to SF for @aidotengineer next week! let’s hang :) We're hosting a BabyAGI x Physical AI Happy Hour with @yoheinakajima on June 30th, 6PM in SF! If you're building across AI agents

arXiv:2606.19336v2 Announce Type: replace Abstract: Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, rese

arXiv:2606.26154v1 Announce Type: cross Abstract: Autonomous microrobots navigating biological vasculature could enable targeted drug delivery and thrombolysis, yet training control policies for reali

arXiv:2606.26418v1 Announce Type: new Abstract: A non-agentic 'oracle' AI that estimates probabilities of future events faces a self-reference problem: once its answer is learned and acted upon, it ca

We’re getting together with @Zai_org for a FIFA World Cup watch party ⚽️ USA vs. the world on a big screen, food and drinks on us, and a fireside chat on open-weight models and where agentic coding is

arXiv:2606.25394v1 Announce Type: new Abstract: Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We form

if you get 1% better every day then you're 37x better in a year (from @JamesClear's atomic habits book) my theory is you can do this for agents if you build a good continual learning loop which is wha

Just had a great discussion on dynamic workflows. Rough notes: - applies to a very small set of use cases - think of it as a new paradigm of (test-time compute) TTC - strong for hill-climbing research

arXiv:2601.03509v2 Announce Type: replace Abstract: We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of ex

arXiv:2606.23961v1 Announce Type: new Abstract: Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every

Grok Build just got another update with many improvements Release Notes: v0.2.64 — 2026-06-24 Features: • Dashboard now displays the current directory and branch; click or press Ctrl+L to change locat

What is actually limiting model routers for coding tasks? Most routers treat picking a model as a static, one-off classification. This paper identifies the real bottleneck as information deficit. Simp

arXiv:2407.18957v5 Announce Type: replace-cross Abstract: Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroe

arXiv:2606.20955v1 Announce Type: new Abstract: Dynamic average estimation is a critical problem in multi-agent systems, enabling agents to collaboratively estimate time-varying signals using only loc

arXiv:2606.21153v1 Announce Type: cross Abstract: Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion

arXiv:2606.20960v1 Announce Type: cross Abstract: Nash equilibrium (NE) arises from selfish utility maximization, yet its social welfare can be arbitrarily far from optimal. Moreover, computing an NE

When Amazon Web Services Inc. held its New York Summit last week, Vice President of Agentic AI Swami Sivasubramanian as usual was the headline act, delivering the opening keynote. Sivasubramanian made

arXiv:2606.21173v1 Announce Type: new Abstract: Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: instead of learning a model of the transition kernel P

Let the smart horses build their own harness. See my previous article on this: https://x.com/Kangwook_Lee/status/2052925157606568217 🧠Self-Harness: Harnesses that improve themselves New paper on agent

arXiv:2606.21024v1 Announce Type: cross Abstract: AI-assisted research systems generate many failed attempts, but those failures rarely become a durable, shared knowledge asset. We propose a negative

Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations. I believe the strongest

I’m running a 3 hour advanced workshop at AI Engineer World’s Fair! 🚀 2026 has greatly changed how one should learn lower-level technicals like kernels, agentic RL, reward hacking, cont learning. What

it's official, I'm on community at NousResearch. I'll be shipping tested walkthroughs, answering questions and carrying what the community builds back to the team. if you're on Hermes Agent, the Disco

OMG! Fugu Ultra is ridiculously good at these 3D renders. Media Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our ‘Fugu Ultra’ model matches the p

This morning on Hacker News I saw Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance, describing a small but effective inpainting model - a model where you can mark region

The @aiDotEngineer schedule wins for having the most possible ways that developers can interact with it: JSON, llms.txt, MCP server, iCal, embeddings, agent skill https://ai.engineer/worldsfair/schedu

Had the pleasure of meeting @jerryjliu0 at a @llama_index meetup in SF. We talked about document parsing and vector search market. 🌉 DM if you wanna meet in SF. Would love to chat about search, agents

arXiv:2606.12147v1 Announce Type: new Abstract: We consider the problem of engineering autonomous intelligent agents that are capable to responsibly not comply with user requests. We argue that machin

arXiv:2606.11350v1 Announce Type: new Abstract: Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and

arXiv:2606.09867v1 Announce Type: cross Abstract: Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the auto

first in a series of technical blogs of how we build llm infra How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latenc

i showcase 'controlled' self improvement with a novel regime-to-seam approach where failures are categorized and allowed to fix targeted areas of the agent while interesting, it's more to showcase the

Lium, a startup formerly known as Astromind, today announced the launch of an “agentic harness” that helps large language models dig into the most complex and messiest datasets. The launch comes after

my weekend hobby: self improvement research in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improving agents 'Regimes: An Auditable, He

arXiv:2606.10875v1 Announce Type: new Abstract: Large language models (LLMs) rely on tool use to act as autonomous agents, yet often fail in multi-step execution due to insufficient tool-related knowl

arXiv:2606.10456v1 Announce Type: cross Abstract: AI-control monitors score individual agent actions to detect misbehavior, but real harm can be distributed across many benign-looking steps, each indi

Zscaler Inc. today unveiled a major expansion of its zero-trust SASE platform, adding an agentic framework that lets administrators manage the system through natural-language prompts and extending its

arXiv:2605.22763v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A m

As enterprise AI budgets hit their limits earlier each year, the pressure to fund new agentic and inference workloads without expanding total spend is forcing a fundamental rethink of infrastructure a

arXiv:2605.11484v2 Announce Type: replace Abstract: Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over

arXiv:2606.08450v1 Announce Type: new Abstract: Financial portfolio trading is naturally formulated as a reinforcement learning problem, where an agent sequentially rebalances assets under changing ma

arXiv:2606.09620v1 Announce Type: new Abstract: Planning collision-free motion for large robot fleets is difficult because collision avoidance induces strong inter-agent coupling that grows rapidly wi

Puffy participated in a pickleball event on June 30 in San Francisco called 'The Agent Open,' which was co-hosted with Good Friends. The event appears to have been organized or promoted through Luma,

arXiv:2606.09399v1 Announce Type: new Abstract: We present SUPERBROWSER, an autonomous web-navigation agent designed against a single guiding hypothesis: a web agent should browse the way a person bro