Knowledge catalogue
Harness distillation can train general scaffolding into a model. The harness that remains is the part tied to your tools, data, users, and environment. The post Are agent harnesses dying? What harness
arXiv:2609.34060v1 Announce Type: new Abstract: Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks. However, age
arXiv:2609.31760v1 Announce Type: cross Abstract: Can a robot improve itself the way coding agents now improve software? We built an agentic system to find out. It watches a robot fail, works out whic
Apropos NVidia’s agent trust framework, anybody remember NemoClaw? Anyone using it? Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed w
arXiv:2609.31531v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and
We are proud to be launch partners for NVIDIA Open Agent Safety Platform. We believe safe and responsible AI development is critical as the use of agents scale and they get more prevalent. Together AI
arXiv:2609.29366v1 Announce Type: new Abstract: Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewe
If somebody whacks you in the face with a crowbar, are you going to put the crowbar in jail, or sue the crowbar? If an 'AI agent' breaks into your computer, who are you going to charge or sue? The 'AI
Super interesting paper from Google and colleagues. It studies where it's possible to distill an agent harness. With the specialized harness removed, macro task success goes from 23.3% to 44.3%. That
I am creating a local AI agent called 'Ontelic' for Windows. Ontelic returns to Ollama and also manipulates the actual Chrome. This is not for promotion but to share what we've learned. I'll give GitH
arXiv:2609.24974v1 Announce Type: cross Abstract: Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain
Meta's Muse AI agent has been blocked from shopping Amazon on behalf of its users, GeekWire reports. A popup message started appearing on Sunday for Muse users saying that 'continued access by an unau
LittleHorse Enterprises LLC, a maker of workflow orchestration software spanning multiple applications, today announced version 1.3 of its Saddle Command Center, adding no-code agent deployment, prebu
arXiv:2609.20347v1 Announce Type: cross Abstract: LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes diffi
arXiv:2609.18126v1 Announce Type: new Abstract: Agentic AI systems often approach the same task through multiple workflows that differ in reasoning strategy, verification structure, and compute cost.
MLPerf Inference v6.1 introduced the first agentic workload run on datacenter hardware and evaluated a model with more than one trillion parameters (Kimi K2), setting a new benchmark for scale. The te
arXiv:2609.16487v1 Announce Type: new Abstract: We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid s
arXiv:2609.13406v1 Announce Type: new Abstract: When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intellig
The LA Agentic AI Meetup in on the Tech Week calendar. Join us Tuesday, October 13, 5 to 7pm at Gulp in Playa Vista, for a few live demos, drinks, and real people comparing notes on what they're build
arXiv:2609.15397v1 Announce Type: new Abstract: AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative executio
Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real-time email threat detection at billion-message scale, plus t
Live now: our Harness Engineering Track from AI Engineer World's Fair 2026. Ports, proofs, kill switches, and what is left of an agent when you remove the model. Thesis: when an agent breaks in produc
arXiv:2609.12818v1 Announce Type: new Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal
arXiv:2609.09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read
arXiv:2609.05552v1 Announce Type: cross Abstract: Industrial environments increasingly rely on collaboration between humans and AI-enabled agents. Effective teamwork requires aligning how agents perce
arXiv:2609.07925v2 Announce Type: new Abstract: We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained
arXiv:2609.08273v1 Announce Type: new Abstract: Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuou
Databricks Inc. today expanded its Adaptive Instructed-Retriever search model to speed up response times for requests from artificial intelligence agents that require multiple rounds of retrieval. The
While GPUs remain essential for LLM training and inference, enterprise‑scale agentic AI workloads shift the focus to orchestration rather than raw compute. Agents must break down requests into subtask
Great to see Stripe’s platform and agent for knowledge work, Kai, get featured on Claire’s show! My favorite use case was asking it questions to slice and dice Stripe’s enormous dataset daily. In fact
arXiv:2609.04170v1 Announce Type: new Abstract: Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this s
arXiv:2502.18407v2 Announce Type: replace-cross Abstract: Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, s
arXiv:2602.09341v2 Announce Type: replace Abstract: Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outpu
I read AI papers for a living, but it has become impossible to track insights. Every week I triage agent papers for our Top AI Papers of the Week digest. A few weeks ago, I tried @viktor_com, an AI em
arXiv:2609.03109v1 Announce Type: new Abstract: Current AI agents compellingly describe slides. However, AI-assisted slide editing requires more than understanding: the output must retain layout, styl
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
arXiv:2609.02750v1 Announce Type: new Abstract: Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite stro
arXiv:2609.00060v1 Announce Type: cross Abstract: Agent payment protocols are emerging as a key transaction layer for autonomous commerce, enabling AI agents to purchase goods and services and execute
arXiv:2609.00731v1 Announce Type: new Abstract: Recent advances in LLM agents enable a new paradigm for asset pricing, which we call Agentic Empirical Asset Pricing (AEAP): systems that autonomously c
arXiv:2609.01289v1 Announce Type: new Abstract: Hyperspectral unmixing is a key task in remote sensing that aims to decompose mixed pixels in hyperspectral images into their constituent material signa
Banger paper from ByteDance Seed. If you are curious about self-evolving agent harnesses, this one is worth your time. (bookmark it) The proposes method, HarnessDev, stops scoring a model on the tasks
arXiv:2609.01491v1 Announce Type: cross Abstract: The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implica
arXiv:2609.01035v1 Announce Type: new Abstract: Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a br
arXiv:2608.30369v1 Announce Type: new Abstract: We present OLIVE, a framework for adapting a foundation model to provide real-time assistance in temporally demanding, high-stakes, and dynamic tasks. W
arXiv:2608.25937v2 Announce Type: replace Abstract: Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is diff
arXiv:2608.28631v1 Announce Type: new Abstract: An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model fam
arXiv:2608.29814v1 Announce Type: new Abstract: Modern video generators excel at synthesizing individual clips, but complete video production requires coordinating a long sequence of interdependent cr
arXiv:2602.00685v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and
arXiv:2608.28553v2 Announce Type: replace Abstract: Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatio
arXiv:2608.29381v1 Announce Type: cross Abstract: AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are cos
arXiv:2608.28597v1 Announce Type: new Abstract: Online surveys are a foundational data collection instrument in a variety of fields, with attention checks serving as critical guardians of response qua
arXiv:2603.29678v3 Announce Type: replace Abstract: We observe that an agent trace is a structured document. A coding agent session contains user turns, assistant text, chain of thought blocks, tool c
arXiv:2608.26939v1 Announce Type: cross Abstract: Space-efficient warehouse layouts often contain single-agent-width aisles and dead-end workstations where robots have few places to wait without block
arXiv:2608.26683v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although
I'm actually curious if it's that scary to be in the #1 camp * I still think humans will use software instead only doing work through agent apps. So humans will continue to use SaaS through the UI and
Nutanix Inc. today introduced new capabilities intended to help enterprises run agentic artificial intelligence applications alongside existing virtual machines and containerized workloads without spl
arXiv:2501.13200v2 Announce Type: replace-cross Abstract: Coordination in decentralized multi-agent reinforcement learning (MARL) necessitates that agents share information about their behavior and in
arXiv:2608.23541v1 Announce Type: cross Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-
In this installment of Rise of the AI Engineer, Stuart Sy from OpenAI, explains why the bottleneck has moved off the model and onto context, evals, and observability. The post Why better models don’t
arXiv:2608.20597v1 Announce Type: cross Abstract: Agentic AI systems are being procured for military command and control (C2) under public commitments to rigorous testing and human oversight. Whether