Search: “agents”

arXiv:2605.08442v1 Announce Type: cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions in

arXiv:2605.08477v1 Announce Type: new Abstract: Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external dat

arXiv:2605.10663v1 Announce Type: new Abstract: Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactio

Marina Temkin / TechCrunch: Exaforce, which uses AI agents to detect and thwart cyberattacks, raised a 125M Series B at a 725M valuation, bringing its total funding to $200M — As bad actors weaponize

arXiv:2605.08538v1 Announce Type: new Abstract: Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory

LiteParse is the best open-source, model-free document parser for AI agents. Run it over over 50+ document types, and it will parse dense pages with complex text layouts and tables, and it will extrac

arXiv:2605.09252v1 Announce Type: new Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latenc

arXiv:2605.08374v1 Announce Type: new Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval

arXiv:2605.09915v1 Announce Type: cross Abstract: The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a c

arXiv:2605.08468v1 Announce Type: cross Abstract: Local LLM-based coding agents increasingly work in settings where correctness is earned through execution feedback, persistent state, and bounded repa

Francois Chollet argues that symbolic learning represents a fundamental alternative to gradient descent and neural networks rather than a replacement for coding agents, offering a low-level, general-p

@trq212: An Anthropic engineer argues HTML is a better output format for AI agents than Markdown, citing information density, ease of sharing, and two-way interaction — Using Claude Code: The Unreason

arXiv:2512.09629v2 Announce Type: replace Abstract: We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language a

For browser-use AI agents, every task is dozens of model calls in a tight loop. The inference layer isn’t background infrastructure. It’s what the product runs on. @yutori_ai runs Scouts, Delegate, an

arXiv:2605.06908v1 Announce Type: cross Abstract: Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidenc

arXiv:2605.06822v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationa

Start 'claude agents' in a high level directory with all your repos in it (for me thats ~/Projects). It keeps track of which sessions need your input and makes it really easy to resume and pick up whe

Swap models & view their capabilities! Try out in Deep Agents CLI: https://docs.langchain.com/oss/python/deepagents/cli/ here's model profile details look like in practice, using @NVIDIAAIDev's Nemotr

arXiv:2605.06761v1 Announce Type: new Abstract: The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection at

Fortune: Q&A with Qualcomm CEO Cristiano Amon on 2026 as “year of agents”, the end of the smartphone-centric world, 6G turning humans into “walking cameras”, and more — Cristiano Amon's pitch is that

New research: long-running agents often fail by stopping too early, not because the model can't make progress. We tested 5 harness designs across 8 long-horizon coding tasks. Our new orchestration har

Today, we're announcing a preview of Amazon Bedrock AgentCore Payments, a new set of features in Amazon Bedrock AgentCore that enables AI agents to instantly access and pay for what they use. AgentCor

Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK. We’ve used it to: - Autoresearch our internal skills, cutting token use by 20%

Most teams can build agents, but far fewer have the infrastructure or know-how to run them reliably in production. Join us for an evening in San Francisco on May 19th, with Victor Moreira + @Vtrivedy1

Our new voice models are now available in the Realtime API: 🎙️ GPT-Realtime-2: Build production-ready voice agents that can think harder, take action, handle interruptions, and keep conversations flow

AI agents often struggle to plan movements because their internal representations of the physical world can be overly tangled. CDS PhD student Ying Wang (@yingwww_) shows how straightening these pathw

As agents generate more code, review is becoming the bottleneck. You can write a PR in minutes, but understanding whether it's correct, safe, and ready to merge still takes longer than writing it. Dev

Continuous-video agents (computer use, robotics, static scenes) burn compute re-ingesting pixels that didn't move. VLMaxxing teaches a frozen video VLM to skip the reruns. 54 fps perception on Gemma 4

arXiv:2510.12061v2 Announce Type: replace Abstract: Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generaliz

arXiv:2605.02943v1 Announce Type: new Abstract: Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisio

I ❤️ NYC We're hosting two in-person events next Wednesday: 1️⃣ FinParse workshop: Build AI agents to extract and act over the most complex financial documents 2️⃣ AI Happy Hour with Tabs: drinks, con

.@ListenLabs Co-Founder & CTO @florian_jue on the 2 types of engineers who build great agents: 1/ Those who know what LLMs can and can't do, and can feel when something's off 2/ Product engineers who

omg @bcherny with banger quotes “the future is more async agents… this is why we emphasize verification” “if you’re familiar with higher order functions, routines are higher order prompts” “default is

By sharing datasets on @huggingface, you help agents being able to analyze them, giving everyone the ability to make sense of complex data. For example, this is some of the insights I uncovered from @

arXiv:2605.02815v1 Announce Type: new Abstract: Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Mo

arXiv:2602.04737v2 Announce Type: replace Abstract: This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet ra

Sure looks like Bun is at least exploring a port from Zig to Rust given this docs/PORTING.md guide for coding agents https://github.com/oven-sh/bun/blob/46d3bc29f270fa881dd5730ef1549e88407701a5/docs/P

Agents are now the primary consumers of knowledge infrastructure. Tomorrow @jennapederson, Arjun Patel, and @RoieSchwabco are going live here to talk about what that means for your stack, share this w

Kate Rooney / CNBC: Bret Taylor's Sierra, which sells AI customer service agents, raised a 950M Series E led by Tiger and GV at a 15.8B post-money valuation, up from $10B in 2025 — Artificial intellig

Congratulations to @ashashutosh, @EdoLiberty, and the @pinecone team on the launch of Nexus, a knowledge engine for agents. They’ve spent years building at the core of AI infrastructure, and Nexus ref

arXiv:2605.00356v1 Announce Type: new Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every t

Jason Lemkin / SaaStr: A look at Atlassian and Twilio earnings beats, with early signs of Atlassian's AI response success and Twilio becoming a picks-and-shovels layer for AI agents — So this week two

Allie Garfinkle / Fortune: Avoca, whose AI agents let physical services businesses handle inbound calls and dispatch, raised 125M+ across seed, Series A, and Series B at a 1B valuation — Tyson Chen an

OpenAI announced a feature that allows users to quickly import their existing workflow configurations, including settings, plugins, agents, and project configurations, into Codex with minimal effort.

arXiv:2604.27819v1 Announce Type: new Abstract: Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into c

arXiv:2604.28048v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting p