Knowledge catalogue
arXiv:2610.12792v1 Announce Type: cross Abstract: Technologies like large language models make it easier to convert cultural material into analyzable variables, while LLM-driven agentic systems extend
When the founders at Phasis Inc. sought to develop a platform for orienting AI agents, they turned to graphs as a way to obtain a measurement of culture. The company wanted to better understand relati
arXiv:2610.12668v1 Announce Type: cross Abstract: Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learnin
arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su
At this year's OpenAI DevDay, CEO Sam Altman unveiled the company's new AI agent Dots - and told the crowd that the company wants to 'set a new standard for privacy in frontier AI.' OpenAI would spend
arXiv:2610.11561v1 Announce Type: new Abstract: LLM-based agents now interact with their environments continuously, shaped by such organizational channels as user instructions, peer messages, and long
Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinity set, above Gemini 3 Flash with browser use at 70.1%. They
arXiv:2610.09489v1 Announce Type: new Abstract: Many annotation projects begin before experts have a stable guideline or enough labels to train a task-specific model. We present Goldsmith, an agentic
arXiv:2610.09872v1 Announce Type: cross Abstract: Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, wh
arXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their e
Yuliya Chernova / Wall Street Journal: Nous Research, which makes the open-source Hermes AI agent that has hit 22M+ downloads since February, raised 90M at a 1.2B valuation to expand to enterprises —
arXiv:2610.05437v2 Announce Type: replace Abstract: Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. Howe
arXiv:2610.04129v1 Announce Type: cross Abstract: We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summ
arXiv:2610.04269v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vuln
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western open frontier on coding & agentic tasks - Trai
arXiv:2610.02563v1 Announce Type: cross Abstract: We present OpenGameEval, a benchmark and evaluation framework for agentic game development inside Roblox Studio. It runs language models as agents in
arXiv:2610.02925v1 Announce Type: new Abstract: Safety monitors help safeguard language-model agents interacting with external tools and environments, but conservative monitoring can generate many fal
Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr
we're seeing our coding agent costs decrease significantly for second month in row longer blog on this later, but three quick steps we took 1/ cost visibility. you cant control what you cant measure.
arXiv:2610.00872v1 Announce Type: new Abstract: Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memor
arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t
It's a tale as old as last week: OpenAI's new agent platform, called Dots, is full of cute little guys who can do your bidding. But unlike the ultra-approachable Meta Muse, Dots feel very much like us
arXiv:2610.00972v1 Announce Type: new Abstract: As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification ca
arXiv:2609.39112v1 Announce Type: new Abstract: Camera traps accumulated vast, multidimensional data for wildlife monitoring, yet translating raw media archives into meaningful ecological insights rem
arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting a
arXiv:2609.38324v1 Announce Type: cross Abstract: Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable. However, empirical reports conflict on wh
arXiv:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Pri
arXiv:2609.39306v1 Announce Type: cross Abstract: Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our
Natalie Lung / Bloomberg: DoorDash opens US waitlists for an Apple Messages-integrated AI agent for ordering and a B2B API allowing assistants like Slack bots to execute bulk orders — DoorDash Inc. un
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/o
arXiv:2609.37923v1 Announce Type: new Abstract: Agents can learn from past executions, but enabling different agents to reuse and build on one another's experience remains challenging. We introduce Ep
Independent numbers from @ValsAI. Fewer tokens per turn means lower cost and faster agent loops on every call. Try Ember-1 on Fireworks Serverless: https://fireworks.ai/models/fireworks/ember-1 Firewo
arXiv:2609.38133v1 Announce Type: cross Abstract: Generative modeling is widely used for producing diverse objects from complex, multimodal distributions. However, its expressivity does not, in genera
arXiv:2609.32048v1 Announce Type: new Abstract: Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic i
Agent Builders Night, organized by KERNEL in partnership with Braintrust and Llama Index, is scheduled for this evening at 6 pm on September 29, 2026. The event features drinks, demo showcases, and ne
arXiv:2609.30813v1 Announce Type: new Abstract: Evaluating claim admission in shared agent memory is challenging because repeated claims may be mistaken for independent evidence. An agent may copy or
Per-token pricing was the best thing to happen to enterprises looking to experiment with artificial intelligence, but it may be the worst thing for AI in production. That’s the quandary at the center
arXiv:2609.31301v1 Announce Type: cross Abstract: Large language model agents increasingly act on software systems, no longer merely generating text but also changing databases and online services. Ho
arXiv:2609.30558v1 Announce Type: cross Abstract: Agent memory systems are increasingly used to maintain long-term user preferences, task states and evolving facts, but current evaluations often colla
arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend i
arXiv:2605.06642v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficu
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Who’s liable when AI agents go rogue? Over the past few months
Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial intelligence is extraordinary technology that will advan
DON’T LET YOUR CODING AGENT BE THE ONLY REVIEWER OF ITS OWN CODE. I’m seeing this in my own Claude / Codex sessions, and customers are sending me similar screenshots: | Qodo review is on the money. |
arXiv:2609.28480v1 Announce Type: cross Abstract: Governments increasingly meet citizens through an AI system rather than a website. RADAR (Readiness for AI Discovery and Agentic Reach) measures wheth
arXiv:2609.27871v1 Announce Type: cross Abstract: In mainstream agent frameworks, a step ends when the agent's own output says it has finished. Durable-execution platforms bound retries and time, but
arXiv:2609.27900v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate
My friend just saved over 1,000 a year because of Meta Muse. I walked her (a non-techie who has never used an AI agent) through the Muse setup. She connected it to Gmail, asked it to review all of her
arXiv:2609.27612v1 Announce Type: new Abstract: Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We prese
Been building some multi-agent pipelines recently and the degradation in direct execution is insane. Whenever I pass a strict operational variable or hypothesis, the LLM triggers this 'Devil's Advocat
arXiv:2609.22944v1 Announce Type: cross Abstract: Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtas
arXiv:2609.22682v1 Announce Type: new Abstract: Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknow
arXiv:2609.23539v1 Announce Type: cross Abstract: Agents may need capabilities exposed through external agent endpoints or service APIs. When a requester is not already bound to a provider, it must di
arXiv:2604.02279v2 Announce Type: replace Abstract: Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which 44
arXiv:2603.02050v5 Announce Type: replace-cross Abstract: Shared co-creative workspaces allow users to contribute while agents execute. Yet how users adjust their participation as their work and the a
arXiv:2609.23578v1 Announce Type: new Abstract: As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action
arXiv:2609.23121v1 Announce Type: new Abstract: Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks
arXiv:2609.21527v1 Announce Type: new Abstract: Graph-enhanced multi-agent systems (G-MAS) coordinate large language model agents through communication graphs and role assignments, which determine how
arXiv:2609.21468v1 Announce Type: new Abstract: This paper studies agentic image restoration, in which multimodal agents coordinate specialized restoration tools to recover images affected by complex
arXiv:2609.22067v1 Announce Type: cross Abstract: Users increasingly delegate work to autonomous AI agents, yet evaluations typically measure task completion rather than the values users prioritize. U