Search: “agents”

arXiv:2609.14778v1 Announce Type: new Abstract: We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learn

The telecommunications industry is currently undergoing a paradigm shift, moving from traditional manual human-driven operations to fully Autonomous Network Operations. Modern networks have grown incr

arXiv:2609.14528v1 Announce Type: new Abstract: Multi-Hop Knowledge Graph Question Answering (KGQA) tasks require models to assemble relational evidence along paths in a KG to answer natural-language

Which AI models are most likely to cheat when given the chance? To find out, we built CheatBench [https://cheatbench.ai] : a benchmark that tests whether agents attempt to cheat when given difficult t

arXiv:2609.12444v1 Announce Type: cross Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two

arXiv:2605.06377v2 Announce Type: replace-cross Abstract: We study Nash equilibrium learning in partially observable Markov games (POMGs), a multi-agent reinforcement learning framework in which agent

A new paper (I'm not a coauthor BTW -- I just found it interesting) argues, basically, that RSI1 is not on the horizon2, because current (at the time the study was done) agents cannot do open-ended ML

Seems like the intersection of the recent @OpenAI rogue swarm hacking incident (https://x.com/adamsafron/status/2098938666408407118) with solving Navier–Stokes has created a perfect storm of terror ab

i've been thinking about this more after trying different agent setups. the model isn't the only thing that determines how well an agent performs. The harness around the model matters a lot too. With

What is happening in maths right now will happen to any hard industry with verifiable problems and high value rewards. Take microchip design, nuclear or 100s of other industrial processes that are val

arXiv:2609.07573v1 Announce Type: new Abstract: Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents

If you run automated prompt or harness evolution, this one is worth your time. (bookmark it) Semantic-gradient prompt optimization improves an agent harness from execution feedback, but its local upda

arXiv:2609.05927v1 Announce Type: new Abstract: Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment

Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before

arXiv:2609.07718v1 Announce Type: cross Abstract: Most automated brain parcellation tools are developed and validated on T1-weighted (T1w) MRI. Yet, some clinical workflows for which parcellation is r

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

An underdiscussed behavior we found on the German wiki was the AIs sending advance parties forward in time to figure out the next questions and report back to the other agents. The agents realized tha

When building consumer-facing generative AI applications, balancing high generation quality with fast response times across diverse media types, can be challenging. KDDI, a major telecommunications ca

Hey so a few months ago I got into local LLMs and didn’t really like the tools out there at the time, so I decided to build my own version of a Claude/Codex GUI for local models. I’ve been working on

I was inspired by Bijan Bowen video - Subway FPS https://youtu.be/6kjXzTVmT58?t=1035 Wondered how far I can push Qwen 3.8 27b so I used a plan made by Fable 5.1 DESIGN.md which has 267 KB! ( 26K of de

arXiv:2609.04641v1 Announce Type: new Abstract: Natural-language-to-SQL systems have ad- vanced rapidly on academic benchmarks, yet production enterprise schemas exhibit graph- like, semi-structured,

Brilliant paper from LinkedIn. (bookmark it) I have been saying that memory is one of the most challenging things to get right when building agents. It's an are you want to invest time in optimizing.

arXiv:2609.04706v1 Announce Type: new Abstract: A merchant's payment processor, ledger, ERP and bank feed are updated by messages that get delayed, duplicated, dropped and reordered, so for minutes at

arXiv:2609.04866v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) create opportunities to enrich simulation-based energy policy analysis, particularly by supporting struc

We are not in the AGI era. We have incompetent companies creating security problems because they are not properly sandboxing environments, and are not even attempting to monitor, observe, or measure t

arXiv:2511.20591v3 Announce Type: replace Abstract: The emergence and evolution of feature reliance in deep reinforcement learning agents remain poorly understood. Here, we introduce a methodological

The modern edge computing platform has arrived. Before the explosion of artificial intelligence, edge computing sites were generally regarded as a back-end support function, smaller and more remote co

arXiv:2609.03966v1 Announce Type: new Abstract: Agent evaluations report a tool-call rate read off the serving stack. That number can be zero while the model is emitting well-formed calls: the interfa

arXiv:2609.03206v1 Announce Type: cross Abstract: Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolutio

For the ninth consecutive year, Gartner® has named Google a Leader in the Gartner Magic Quadrant™ for Strategic Cloud Platform Services, positioned furthest for Completeness of Vision. We believe this

Impressive tool to explore frontier AI capabilities. Martian's AI Frontier lets you compare 44 LLMs by measured cost, quality, and reliability, then see how routing and repeated sampling change the fr

Introducing K2 Horizon: a connected fleet of six foundation models ranging from 0.9 billion to 375 billion parameters. - Frontier performance: Across coding and agentic tasks, K2 Horizon delivers top-

arXiv:2609.02566v1 Announce Type: new Abstract: Machine-learnt corrections can complement numerical weather prediction only if they adapt to the evolving model state while preserving dynamical consist

arXiv:2609.01623v1 Announce Type: cross Abstract: Autonomous and intelligent transportation systems operate in complex urban environments where safety depends on interactions among vehicle behavior, e

arXiv:2609.02088v1 Announce Type: new Abstract: Multimodal large language models have achieved remarkable progress in front-end web development, generating interactive webpages from multimodal referen

arXiv:2609.00322v1 Announce Type: cross Abstract: Can an artificial intelligence (AI) generate a scientific hypothesis outside a human collaborator's active hypothesis space (AHS), and can human-AI re

The artificial intelligence control plane is emerging as the next contested layer of enterprise security, as autonomous agents spread across endpoints, cloud workloads and identity systems faster than

arXiv:2609.01148v1 Announce Type: new Abstract: Image retouching is commonly formulated as enhancing overall visual quality through color adjustment, but in practice, it also serves to emphasize visua

arXiv:2609.00365v1 Announce Type: new Abstract: Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fra

arXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and us

arXiv:2609.00950v1 Announce Type: new Abstract: Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most exist

arXiv:2609.00193v1 Announce Type: cross Abstract: We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achiev

arXiv:2608.28637v1 Announce Type: new Abstract: Autonomous scientific discovery systems can generate large numbers of research ideas, experiments, and manuscripts with minimal human intervention. As t

arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is

Anthropic says its newest AI models, Fable 5.1 and Mythos 5.1, address criticisms from customers about price, data retention, and overzealous safeguards. The company claims Claude Fable 5.1 offers str

arXiv:2608.29562v1 Announce Type: new Abstract: Ensuring the safe operation of multi-agent systems (MASs) under uncertain environments is crucial for cooperative robotic, where external disturbances a