Knowledge catalogue
Great report on LLM agent communication protocols. Communication is a huge bottleneck in multi-agent systems. (worth bookmarking) The report builds a five-dimensional taxonomy (counterparty, payload,
arXiv:2510.09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of re
arXiv:2606.06460v1 Announce Type: cross Abstract: As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to
AI21 Labs discusses how the order of operations in agent pipelines affects performance, presenting findings that reversing the typical 'scale first, enrich second' approach by instead enriching agent
Can we design legal agent verifiers that are up to 1,000x cheaper? Verifiers are LLM judges that check an agent’s work against rubric criteria: they're used both in agent benchmarking and as reward si
AI agents possess incredible reasoning capabilities and can perform increasingly complex actions. But the reliability of agentic outcomes depends entirely on the quality of the context they can access
Agent actions that aren't on your allowlist or can't be sandboxed go to a classifier subagent. This separate agent decides whether to allow the tool call, try a different approach, or ask you for appr
arXiv:2605.27428v1 Announce Type: new Abstract: Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time
arXiv:2605.24693v1 Announce Type: new Abstract: Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive mu
System scaling is the next real bottleneck in agentic AI. If you build agent orchestration layers, this is a clean map of where the engineering leverage actually sits. The labs own the model. You own
Plugins can also affect the empty state of the new menu - the latest datasette-agent adds a form for kicking off a new agent conversation - live demo (if you sign in with GitHub) on https://agent.data
arXiv:2605.22208v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting
arXiv:2605.20442v1 Announce Type: cross Abstract: Generative AI systems are increasingly deployed as interactive agents in online environments, such as a social network called Moltbook. In Moltbook, l
no trace left unread, no issue left unfound 👀 With Engine we’re pointing agentic compute across every trace across every agent so every team can find product feedback, bugs, issues 24/7 langsmith engi
arXiv:2605.15184v1 Announce Type: new Abstract: Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools,
Kimi track - First place: JumpFoundry by @evvaaannnn A Hermes Agent plugin where the designer hand-draws one or two glyphs and Hermes Agent generates the rest, acting as coordinator that routes per-gl
arXiv:2605.10555v1 Announce Type: new Abstract: As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD
arXiv:2605.10448v1 Announce Type: new Abstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to cap
🆕 Hugging Face 🤝 Hermes Agent 🔥 > we added Hermes Agent to local apps: run it locally with any compatible GGUF/MLX model > shipped native traces support for Hermes Agent: visualize your Hermes traces
Hermes Agent now has a new gateway channel! LINE is now an officially supported way to interact with your agent! Read the docs here: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/lin
Your Hermes Agent can now build full videos with the official HyperFrames skill by @HeyGen HyperFrames videos are HTML-native, so your agent has total control over the final output Video made entirely
Not every step in an agent workflow needs the same model. Fleet now lets you customize which model each sub-agent uses, so you can route simple tasks to fast/cheap models and keep stronger models for
arXiv:2604.26997v1 Announce Type: cross Abstract: Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance.
As part of this deployment, you can interact with the agent in several ways We expose the agent via MCP and A2A, as well as with as a 'remote graph' API, which means you can interact with as you would
Highlights: 👉 1M context for long-horizon agentic workflows 👉 Stronger agentic coding across frontend, repo-level, and terminal-based tasks 👉 Multimodal reasoning across text, image, and video inputs
We've open-sourced a few starter projects for you to build on: a coding agent CLI, a prototyping tool, and an agent-powered kanban board. Use Cursor to customize them for your use case: http://github.
arXiv:2604.15184v2 Announce Type: replace Abstract: In the past year, researchers have created agentic systems that can design real-world CAD-style objects in a training-free setting, a new variety of
arXiv:2508.08127v2 Announce Type: replace Abstract: The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collec
Replit's Free Agent feature will be available starting at 5:00am PST on May 2 for a 24-hour period. This announcement likely indicates a limited-time access window for users to utilize the Free Agent
The agentic AI boom has an inconvenient truth: Without a solid data foundation, the revolution stops before it starts. Conversations surrounding an emergent agent control plane signal that agentic AI
arXiv:2601.12979v3 Announce Type: replace Abstract: The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive
arXiv:2604.21744v1 Announce Type: cross Abstract: The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic
arXiv:2604.21480v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as customer-facing agents, yet evaluating their reliability remains challenging due to stochastic
arXiv:2604.20183v1 Announce Type: new Abstract: Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but confl
arXiv:2604.17931v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains
Ryan Gallagher / Bloomberg: Report: China's 360 Digital Security Group has uncovered ~1,000 previously unknown vulnerabilities, including in Microsoft's Office, using an AI-powered agent — A large Chi
This post likely clarifies the distinction between testing platforms and agent platforms, suggesting that a particular tool or framework (possibly LangChain, given Harrison Chase's role) is better cha
arXiv:2604.15468v1 Announce Type: cross Abstract: AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engin
arXiv:2504.12482v2 Announce Type: replace Abstract: The emergence of Agentic Artificial Intelligence (AAI) systems capable of independently initiating digital interactions necessitates a new optimisat
arXiv:2601.20352v3 Announce Type: replace Abstract: The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and comple
Nous Research demonstrated strong performance results using their Hermes agent with Qwen 3.5 35B model on an NVIDIA RTX 4090 GPU, highlighting competitive capabilities of locally-run models compared t
Google LLC’s Android team is introducing new ways to build high-quality software for its mobile platform with artificial intelligence agents. Today, the company provided two new tool suites, including
We are super excited to launch the in-app browser inside Codex with comment mode! View any web pages & iterate with your agent quickly with just point and click. Codex will automatically capture a scr
arXiv:2603.20640v2 Announce Type: replace Abstract: Multi-Agent Debate has emerged as a promising framework for improving the reasoning quality of large language models through iterative inter-agent c
Replit hosted an 'Agent 4 Buildathon Showcase' event, highlighting projects built using Replit Agent 4, their AI-powered development tool that can autonomously build applications from natural language
Databricks explores how agentic AI systems can reason over both structured data (such as tables and databases) and unstructured data (such as documents and text) to answer complex business questions.
arXiv:2604.11641v1 Announce Type: cross Abstract: Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stag
arXiv:2602.04849v2 Announce Type: replace-cross Abstract: We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry an
arXiv:2604.08708v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions
arXiv:2604.04503v3 Announce Type: replace Abstract: Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are es
arXiv:2604.08944v1 Announce Type: new Abstract: Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages
The ‘agent harness’ is essentially the new runtime. It’s like a lightweight OS around an LLM—handling memory, tool calls, retries, and control flow. @hwchase17 im excited about agent harnesses because
Early Beta Support for Blue Bubbles iMsg as a Gateway is now in Hermes Agent. Now you can use iMessage as an interaction layer for your agent. Test early by using hermes update and setting it up! Let
AI agents work best when they reflect the knowledge and judgment your team has built over time. Some of that is institutional knowledge that’s already documented and easy for an agent to use as-is. Bu
Rob Schaper posted a reply on X (Twitter) praising Harrison Chase (@hwchase17) and the LangChain team for their work on agent harnesses, predicting the concept would become widespread within days. ...
We’re partnering with @MiniMax_AI across product and models to make their upcoming releases the best for Hermes Agent users. MiniMax models are already some of the most-used in Hermes Agent. If you ha
arXiv:2610.18780v1 Announce Type: new Abstract: Large language model multi-agent systems extend individual agents' capabilities through collaboration across specialized roles, tools, and workflows. Ye
arXiv:2610.18014v1 Announce Type: cross Abstract: Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. H
arXiv:2610.16067v1 Announce Type: cross Abstract: Agent evaluation harnesses are software systems that run test suites, generate inputs, and decide outcomes with test oracles. This paper audits such s
arXiv:2610.07704v1 Announce Type: cross Abstract: Fully decentralized multi-agent reinforcement learning (MARL), also referred to as independent learning, requires each agent to learn and act using on