agents

Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through multi-agent self-supervision. In this line of research, self

Satya is spot on. The interesting engineering problem isn’t just making models behave, it’s building systems that don’t need to trust them in the first place. We’re working on some pretty fun problems

“The field of artificial life is a very long-term bet on intelligence.” 🐙 Our former intern Akarsh Kumar recently joined @MLStreetTalk to discuss the intersection of evolution and automated search for

**Wild MISSINGNO.** Nous Research has released “Wild MISSINGNO.”, a coding‑and‑agentic reasoning model that emphasizes high token efficiency. It is available for free on the Nous Portal for a limited

arXiv:2610.12360v1 Announce Type: new Abstract: When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusio

arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetti

arXiv:2610.11613v1 Announce Type: new Abstract: An agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component

arXiv:2507.14897v2 Announce Type: replace Abstract: Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However,

arXiv:2501.07440v3 Announce Type: replace-cross Abstract: Paying attention improves performance, but attention is metabolically costly, so how should a resource-efficient agent allocate it? We study o

arXiv:2610.11667v1 Announce Type: cross Abstract: Thermodynamic cycles are the foundation of energy conversion across natural and engineered systems, transforming heat into useful work. However, these

arXiv:2610.10988v1 Announce Type: new Abstract: As agentic systems gain commercial popularity, user simulators increasingly serve as measurement instrument for their evaluation. However, the fidelity

arXiv:2610.11555v1 Announce Type: new Abstract: We study personalized federated linear stochastic approximation (LSA), a framework which notably encompass personalized temporal difference learning. In

arXiv:2610.10657v1 Announce Type: cross Abstract: In subliminal learning (SL), a teacher model passes on a trait to a student model by distillation on data semantically unrelated to the trait. So far,

arXiv:2603.23406v3 Announce Type: replace Abstract: Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, the

arXiv:2610.10604v1 Announce Type: cross Abstract: When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial componen

arXiv:2610.11578v1 Announce Type: cross Abstract: Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experi

arXiv:2610.11577v1 Announce Type: cross Abstract: Autonomous vehicles often suffer from limited perception due to occlusions, blind spots, limited sensor range, and the complex nature of surrounding e

arXiv:2610.11707v1 Announce Type: new Abstract: Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new t

Coding-agent platforms, sandbox products, and code-execution services all need the same thing: isolated machines that start up fast, retain their state between bursts of work, and don’t consume comput

arXiv:2610.11152v1 Announce Type: cross Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often desc

arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, whil

arXiv:2610.12086v1 Announce Type: new Abstract: LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often compu

arXiv:2610.11344v1 Announce Type: new Abstract: Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining stat

arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-au

arXiv:2610.11314v1 Announce Type: new Abstract: Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions. How

going rate for this role is between 5-50m comp package btw at the frontier agent labs literal hardest role to hire for rn and every ai startup wants someone > chronically online (knows trends) > has t

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:2610.11655v1 Announce Type: new Abstract: Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the sys

Building an AI agent that works in a demo is a different problem from running one for 40 million developers. Postman and AWS share the architectural patterns behind Agent Mode: controlling tool sprawl

arXiv:2610.08900v2 Announce Type: replace Abstract: Agentic coding makes code generation cheap, but reliable completion remains difficult: the agent that writes the code is a weak judge of whether it

arXiv:2610.10962v1 Announce Type: cross Abstract: Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied ta

i'm pulling out my suit for this Huge shoutout to @imaanxsultan and everyone else for organizing! The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised co

Before there were cute little guys, there was Instinct. In August, the startup got its AI agent to market with an unusual playbook: invite-only, no marketing, and barely so much as a website. And yet,

arXiv:2610.11704v1 Announce Type: new Abstract: Complete orthogonal predictive coordinates do not by themselves bind a latent direction to a named intervention. We present a mathematical and synthetic

arXiv:2610.11862v1 Announce Type: new Abstract: Mathematicians value proofs for more than correctness: among correct proofs, simplicity, purity and the computational cost of finding them vary widely.

LM Studio 0.4.26 is out now! • ⚡️ `/v1/systemone` and `/v1/decisions` APIs • 👾 Coexistence with Bionic • 🎨 UI updates and bug fixes Yes, you can now point your Bionic agent to models loaded in your LM

arXiv:2610.12196v1 Announce Type: new Abstract: Autonomous racing requires accurate trajectory tracking near the handling limits of a vehicle while maintaining low computational latency. Geometric con

arXiv:2508.12087v3 Announce Type: replace Abstract: Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goa

arXiv:2605.11814v2 Announce Type: replace Abstract: The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-ter

arXiv:2610.11794v1 Announce Type: new Abstract: Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limit

arXiv:2610.10778v1 Announce Type: cross Abstract: Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the informatio

arXiv:2610.04838v2 Announce Type: replace Abstract: As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupl

arXiv:2610.11959v1 Announce Type: new Abstract: Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the

arXiv:2610.11966v1 Announce Type: new Abstract: Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllabl

arXiv:2610.12299v1 Announce Type: cross Abstract: Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings

arXiv:2507.18074v2 Announce Type: replace Abstract: Recent progress in LLM agents has advanced the prospect of autonomous research. Yet whether AI can complete difficult long-horizon tasks, especially