Search: “agents”

The Top AI Papers of the Week (April 6 - 12) - Memento - Neural Computers - The Universal Verifier - Agent Skills in the Wild - Memory Intelligence Agent (MIA) - Single-Agent vs Multi-Agent LLMs - Sca

Agent skills are great. I wanted to share some of my favorites from Jesse Vincent's 'Superpowers' skill pack 𝚠𝚛𝚒𝚝𝚒𝚗𝚐-𝚙𝚕𝚊𝚗𝚜 skill produces much better plans than any harness' built in plan mode that I'

NEW paper from Microsoft Every agent benchmark has the same hidden problem: how do you know the agent actually succeeded? Microsoft researchers introduce the Universal Verifier, which discusses lesson

arXiv:2508.04903v4 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly organized into multi-agent systems for complex reasoning and decision-making tasks. However

arXiv:2609.35557v2 Announce Type: replace-cross Abstract: The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property. The har

arXiv:2610.17723v1 Announce Type: new Abstract: People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a pers

arXiv:2610.12822v1 Announce Type: new Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with

arXiv:2610.11467v1 Announce Type: cross Abstract: We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telem

arXiv:2610.09163v1 Announce Type: new Abstract: Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when u

arXiv:2610.06971v1 Announce Type: new Abstract: Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Pres

arXiv:2610.01108v2 Announce Type: replace Abstract: Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly repro

arXiv:2605.06639v2 Announce Type: replace-cross Abstract: We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and de

arXiv:2609.37017v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natur

AI agent access is complicating identity controls as agents log in, carry credentials and act on someone’s behalf. They have characteristics of both human and machine users. That overlap can make acti

arXiv:2602.16313v2 Announce Type: replace Abstract: Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by

AI is accelerating software development at an unprecedented pace. But as code generation scales, so do the challenges of securing the code, especially emerging AI-based vulnerability exploitations. To

Banger paper from Google on agent harnesses for long-horizon tasks. (bookmark it) Google Research built a many-agent harness for long mathematical proofs, and it produced new results on open problems

arXiv:2609.15009v1 Announce Type: new Abstract: Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better ov

Should you build an agent harness? I see lots of opinions about it. My thoughts: As an AI engineer, learning how to build a harness is one of the best ways to stay ahead and unlock unique value from a

arXiv:2609.10724v1 Announce Type: new Abstract: Sustained deployment of generative AI agents requires more than isolated task success. Agents must remain useful across repeated interactions, changing

arXiv:2609.05279v1 Announce Type: new Abstract: Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that ca

arXiv:2609.02095v1 Announce Type: new Abstract: An AI agent can perform well on benchmarks and still be unsuitable for deployment. Existing AI-agent benchmarks measure whether an agent can complete re

arXiv:2511.15755v3 Announce Type: replace Abstract: Large language models (LLMs) promise to accelerate incident response in production systems, yet single-agent approaches generate vague, unusable rec

arXiv:2608.25593v1 Announce Type: new Abstract: Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/s

For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answerin

arXiv:2608.20438v1 Announce Type: cross Abstract: Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted s

The most important agentic workflows are the ones where you collaborate with the agent, verify its results, and encode them as a skill or verifier for reuse. This works for things like writing, resear

arXiv:2608.17933v1 Announce Type: new Abstract: Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsup

arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these

arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that sys

arXiv:2511.19436v2 Announce Type: replace-cross Abstract: Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary mode

**Agentic Workflows** enable automated systems to execute complex tasks by orchestrating multiple agents that interact with each other and external services. They delegate subtasks, monitor progress,

Learn how to build trustworthy AI agent evals using regression tests, capability evals, production traces, LLM judges, and reproducible environments. The post AI agent evaluation: Tips from Anthropic

arXiv:2607.23678v1 Announce Type: new Abstract: Large language models (LLMs) enable autonomous agents for reasoning, planning, and tool use. Recent systems increasingly organize these agents as graphs

When we introduced the Open Knowledge Format (OKF) in June 2026, we asserted that the context that agents need (table schemas, metric definitions, runbooks) should live in a format, not in a proprieta

Running frontier AI in production is demanding — accelerators to manage, latency to hold steady across continents, regulated data to keep in-region, and long-context requests to serve reliably. Claude

Editor’s note: Some of the most interesting questions in AI are being asked by information theoreticians, around how to provide context to an emerging class of AI agents. A few weeks ago, we waded int

arXiv:2607.06700v1 Announce Type: new Abstract: Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs)

arXiv:2511.02200v2 Announce Type: replace Abstract: The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse ag

my fave question, talked about this coding agent Eval+Improvement loop infra + UX in my AIE talk yesterday! biased but LangSmith is the best spot to Eval + continuously improve your coding agents, and

arXiv:2606.30072v1 Announce Type: new Abstract: Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training w

This post describes an AI research agent built on ActiveGraph that provides complete visibility into its reasoning process through detailed graphs and traces of claims, sources, and internal agent act

arXiv:2606.06011v1 Announce Type: new Abstract: In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasi

arXiv:2511.14460v2 Announce Type: replace Abstract: Large language models (LLMs) have rapidly evolved from single-turn text generators into the foundation of increasingly capable agents. As these agen

👏👏 Introducing Qwen3.7-Plus — a multimodal agent model that unifies vision and language into one versatile agent foundation. ✅ Multimodal interactive hybrid agent: unified GUI & CLI operation across v

Replit Agent builds your app. Squidler tests it like a real user. Replit Agent fixes what's broken. That's the full AI QA loop, and it's now live in Replit's MCP library. You describe what your app sh