Search: “agents”

Yohei Nakajima discusses his exploration of stateful agents and concludes that current implementations have not yet achieved what the concept truly entails, suggesting the field is still in early stag

arXiv:2605.17359v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have shown strong potential for complex reasoning by coordinating specialized agents through struct

arXiv:2605.17526v1 Announce Type: cross Abstract: As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end

arXiv:2605.18693v1 Announce Type: new Abstract: As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether t

arXiv:2601.09413v2 Announce Type: replace-cross Abstract: We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult

This release is absolutely stacked. I want to call out a sleeper feature: Interpreters Imagine your cloud agent gets a 10k-row CSV of support tickets. Without a code runtime, the model is stuck reason

arXiv:2504.07347v3 Announce Type: replace-cross Abstract: As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While

This post explores conceptual parallels between classical distributed systems design patterns—such as actor models and reactive blackboard architectures—and their potential application to LLM agent de

Google Cloud is enhancing its “agent-first” coding platform for developers with the launch of Antigravity 2.0, a new standalone desktop application that enables a full “agent-optimized” user experienc

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-

announcing deepagents v0.6, our biggest release yet! it’s all about performance: at the model layer w harness profiles, agent layer w code interpreter, and at scale w streaming and delta channels cont

Congrats to the @cursor_ai team on Composer 2.5 — a huge milestone for agentic coding models. Together AI, the AI Native Cloud, is proud to partner on this launch. Composer 2.5 is pushing the frontier

arXiv:2605.15315v1 Announce Type: new Abstract: LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at

arXiv:2605.15461v1 Announce Type: cross Abstract: Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Cu

Nebius and @LangChain have partnered to integrate Nebius Token Factory with LangChain's Deep Agents. The integration, combined with LangChain's existing Tavily integration, gives teams building on Lan

arXiv:2605.16194v1 Announce Type: cross Abstract: LLM agents routinely serve as first (and sometimes only) readers of academic papers, skimming for sub-claims, extracting reproducibility steps, and ge

arXiv:2605.15425v1 Announce Type: cross Abstract: Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks such as debugging, root cause analysis, and code r

This post likely discusses Yohei Nakajima's understanding of stateful AI agents—systems that maintain and utilize information across multiple interactions rather than treating each conversation indepe

We gave a full 90 minute workshop on how to build agentic workflows over your enterprise documents at @aiDotEngineer Singapore 🇸🇬🦙 The majority of unstructured information is locked up within PDFs. @h

This post likely discusses how developers often create unnecessarily complex evaluation environments when testing AI agents, and suggests simplifying these setups for more effective testing. The advic

Singapore's head of AI Govtech estimates the country will have 1.3 billion AI agents deployed within the next two years and is actively developing infrastructure to support this expansion. This sugges

Interesting interpretability paper on tool-using agents. The authors probe hidden states and find the model often recognizes it should call a tool, but fails to actually call one. The mismatch ranges

the Codex app is in a category of its own. “agentic excel on mac” is an interesting description. gotta say Codex is completely unrecognizable from 3 months ago. guys went extreme founder mode on this

arXiv:2605.14671v1 Announce Type: cross Abstract: Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate s

// Beyond Individual Intelligence // One of the more useful multi-agent surveys I've read this year. 200+ papers mapped along three axes: collaboration mechanisms, failure attribution, and self-evolut

Three years of enterprise AI investment, and most companies are still waiting for the payoff. Boomi LP thinks it has found it, unveiling Boomi Companion, a collection of open-source agent skills that

arXiv:2605.14133v1 Announce Type: new Abstract: Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend

arXiv:2605.13874v1 Announce Type: cross Abstract: Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they rep

arXiv:2605.14355v1 Announce Type: new Abstract: As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carr

arXiv:2605.14527v1 Announce Type: new Abstract: Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic

arXiv:2605.14421v1 Announce Type: cross Abstract: We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry

arXiv:2603.23129v2 Announce Type: replace Abstract: Godel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We intro

arXiv:2504.11703v3 Announce Type: replace-cross Abstract: AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger una

arXiv:2605.14563v1 Announce Type: cross Abstract: Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding ag

arXiv:2605.13860v1 Announce Type: cross Abstract: Moltbook is a social media platform in which posts and comments are authored exclusively by autonomous AI agents. We present the Moltbook Observatory

arXiv:2605.12925v1 Announce Type: cross Abstract: Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view trea

This article likely provides practical advice on how to effectively give feedback to AI agents or autonomous systems, covering techniques for improving agent performance through constructive feedback

arXiv:2605.13046v1 Announce Type: new Abstract: Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from ele

arXiv:2508.01031v5 Announce Type: replace Abstract: Computer-Aided Design (CAD) is widely used for conceptual design and parametric 3D modeling, but typically requires a high level of expertise from d

arXiv:2605.12507v1 Announce Type: cross Abstract: While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains

arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analy

Great move. If you’re building agents, so much time is spent engineering your way through traces. And then comes the hard to rapidly iterate and figure out the changes needed. 🚀Launching: LangSmith En

if you're an artist or creative wondering how to use agents to accelerate your work, or skeptical that they can: please stop what you are doing and look at the 6 examples in this thread The Hermes Age

arXiv:2605.13037v1 Announce Type: new Abstract: Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rat

Natively-agentic is just one of the perks. The overall experience is a step change from anything out there. And then you add the focus to details, user experience, and how supreme the team behind this

arXiv:2605.13044v1 Announce Type: cross Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, b