Knowledge catalogue
arXiv:2609.19125v1 Announce Type: cross Abstract: Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We
arXiv:2609.17527v1 Announce Type: cross Abstract: An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectiv
arXiv:2609.15818v1 Announce Type: new Abstract: As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human research
arXiv:2609.15161v1 Announce Type: cross Abstract: Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strateg
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
arXiv:2609.08572v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple agents, yet their performance de
Good measurement work on whether retrieved agent skills actually help. They report that agent skills that lift your aggregate score can be hurting every task they touch. The usual way of checking comp
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:2608.26950v1 Announce Type: new Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing
Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the
It’s never been easier to start an AI-powered startup on Google Cloud. You grab an API key from Google AI Studio at breakfast, paste it into Antigravity, and by lunch you’ll have a nascent prototype o
Grok Bot has taken over the entire internet. And for good reason It is an EXCELLENT AI agent But you HAVE to set it up the right way Here are the first 5 steps to make your Grok Bot agent team SUPER p
Today we’re open-sourcing Numbat, an agent-detection and response layer that is designed to work across agent harnesses. Numbat gives security teams visibility into agent activity, with controls to bl
arXiv:2607.22854v1 Announce Type: new Abstract: AI agents are enabling a new paradigm of agent-augmented real-time communication (RTC), where humans focus on high-level collaboration, while agents aut
arXiv:2607.14037v1 Announce Type: cross Abstract: Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-ag
arXiv:2607.12338v1 Announce Type: new Abstract: Agent benchmarks often compare two agents after all tasks have run, but costly evaluations make partial runs tempting. A task fraction alone does not sh
NEW paper from Microsoft and colleagues. Debugging agent trajectories at scale is challenging. This is a clever approach to monitor and improve agents in production. The problem: Finding which step in
Hermes Agent is now in the Cloud! Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live. Running a team? Spin up agents for everyone at your or
arXiv:2512.19458v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly embedded in agentic frameworks for scientific discovery. First-principles materials computation impose
arXiv:2607.05029v1 Announce Type: cross Abstract: Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage informati
Hermes Agent now has no problem with scaling huge multi-agent kanban runs, large concurrent sessions, and more with this new update to database concurrency! Install Hermes Agent or update now and give
Very cool work from @jit_infinity: 🔥Leve: filesystem-first, durable agent framework built on LangGraph. You describe an agent as a directory of files. Leve compiles that directory into an agent and ru
arXiv:2606.10747v1 Announce Type: new Abstract: As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiati
nobody told me Hermes Agent could just... join your Discord VC and talk back for those using Discord w/ Hermes Agent theres a feature where you can just have your Hermes agent jump in on a vc call wit
// Scaling Laws for Agent Harnesses // If you build agent harnesses, this one is worth your time. (bookmark it) Most harness tuning treats every token and tool call as if volume is all that counts. Ne
arXiv:2602.03955v2 Announce Type: replace Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limite
May 2026 update: We’ve refreshed this post to reflect our mid-cycle positioning and the evolution of our platform since the report was first published last November. Last fall, Google was recognized a
The enterprise artificial intelligence stack is getting smarter — but is it getting the context it needs to make agentic AI deployment actually work? The defining problem of the agentic era might neve
// Agentic Harness Engineering // Pay attention to this one, AI devs. (bookmark it) Most coding-agent harnesses are still tuned by hand or brittle trial-and-error self-evolution. This new work introdu
arXiv:2604.23459v1 Announce Type: cross Abstract: Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet i
Just received new reach minis for the Miami office! This is the first robot that goes out to people with agentic software meaning anyone can build any apps with their agents so excited to see what peo
arXiv:2604.19540v1 Announce Type: cross Abstract: Teams of LLM agents increasingly collaborate on tasks spanning days or weeks: multi-day data-generation sprints where generator, reviewer, and auditor
At Google Cloud Next, we’re announcing a range of compute capabilities to enable your core general purpose and AI workloads for the agentic world with higher performance and lower costs. Why it matter
This post discusses a Hugging Face Space that enables replaying AI agent execution traces, contrasting this capability with Netflix's replay functionality to illustrate how agent traces provide differ
Tip of the day: If you need help with configs, settings, setup, usage, exploration, tutorials, or development on Hermes Agent, just type /hermes-agent <prompt> Built in skill that gives your agent all
arXiv:2604.11337v1 Announce Type: cross Abstract: The dominant paradigm of local multi-agent systems -- orchestrated, enterprise-bounded pipelines -- is being superseded by internet-wide agent societi
arXiv:2512.02393v3 Announce Type: replace-cross Abstract: Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines.
DigitalOcean's Gradient AI Platform enables developers to build intelligent documentation agents that can automatically generate, maintain, and query technical documentation using large language model
arXiv:2601.04884v2 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to
Nous Research's Hermes agent framework combines a language model's contextual reasoning capabilities ('this') with an autonomous agent built on their Hermes model series, enabling tool use, multi-step
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
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