Search: “agents”

arXiv:2609.40330v1 Announce Type: new Abstract: Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations ty

arXiv:2609.38753v1 Announce Type: cross Abstract: Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and

arXiv:2609.34603v2 Announce Type: replace Abstract: Does repairing an episode make its experience a better memory for the next task? We transfer the same failed source before and after accepted repair

arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by

arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabora

arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as

arXiv:2609.37454v1 Announce Type: new Abstract: Underwriters in commercial Property and Casualty (P&C) insurance spend 30 to 40% of their time on administrative work rather than risk judgment, and a s

Casey Newton / Platformer: Hands-on with Dots, OpenAI's work-focused agentic product: highly capable and intuitive, with natural-feeling conversations represented as a chat inside ChatGPT — With safet

arXiv:2609.37544v1 Announce Type: new Abstract: Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world

arXiv:2609.37834v1 Announce Type: new Abstract: Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes th

arXiv:2609.32490v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently

arXiv:2609.38024v1 Announce Type: new Abstract: An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent stud

🚨🔥 Congress (@RepJoshG @ValerieFoushee @tedlieu) to OpenAI, Anthropic, Google, Meta, SpaceX on their inadequate reporting of their inadequately-controlled agents: “Your companies have since notified t

arXiv:2609.31715v1 Announce Type: new Abstract: Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the p

arXiv:2609.32213v1 Announce Type: new Abstract: Agent performance depends on both the underlying model and the harness that manages its tool use and execution. Selecting a suitable pair requires accou

Every major security shift ultimately comes down to one question: Who or what is allowed to do this? For most of the past two decades, the answer was a person with a username and password. In the arti

arXiv:2609.35058v1 Announce Type: new Abstract: Effective multi-turn agents require interaction strategies that coordinate information gathering, actions, and feedback over long horizons. GRPO is a re

arXiv:2609.31326v1 Announce Type: cross Abstract: Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and locali

arXiv:2609.30863v1 Announce Type: cross Abstract: The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executin

Only an open ecosystem can guarantee the safety of AI Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial in

arXiv:2412.03072v2 Announce Type: replace Abstract: Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a g

arXiv:2609.29808v1 Announce Type: cross Abstract: In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, estab

arXiv:2603.04756v3 Announce Type: replace Abstract: MOOSEnger is a modeling and simulation AI agent framework for the Multiphysics Object-Oriented Simulation Environment (MOOSE) ecosystem, built aroun

arXiv:2609.29394v1 Announce Type: new Abstract: General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair

arXiv:2609.27234v1 Announce Type: new Abstract: AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the s

arXiv:2609.28216v1 Announce Type: cross Abstract: Agentic engineering systems can edit repositories, run tools and tests, build firmware, synthesize schematics, and prepare deployable or manufacturabl

arXiv:2609.27294v1 Announce Type: cross Abstract: Scaling a language model is not only a question of final quality: the architectural choice determines how much computation is spent during training, p

arXiv:2609.24446v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subseque

arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound b

arXiv:2609.26499v1 Announce Type: new Abstract: Today, progress in open-weight language models enables systems capable of writing, executing and debugging code while still running on a single workstat

Modern life comes with an unending, auto-populating to-do list. It never ceases to amaze me how I can be doing nothing at all, minding my own business, and suddenly something needs to be taken care of

arXiv:2609.23695v1 Announce Type: new Abstract: Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must p

arXiv:2609.23790v1 Announce Type: new Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected token

arXiv:2609.24290v1 Announce Type: new Abstract: Instruction-tuned LLMs faced with underspecified queries often commit to a single interpretation rather than ask for clarification, producing confidentl

arXiv:2609.22212v1 Announce Type: new Abstract: Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessme

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine L

arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and

arXiv:2609.23841v1 Announce Type: new Abstract: Long-horizon robotic search must resolve natural language against heterogeneous, incomplete, and often ambiguous evidence: textual information, prior ma

I’ve been working on making small models more capable at agentic coding and work, because most people in the world don’t have the sort of hardware needed to run 3.8-27B, or even 35B-A3B or 9B dense, a

arXiv:2609.20886v1 Announce Type: cross Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tabl

BREAKING: Grok 4.7 dominates the Legal Agent Benchmark. It scored 19.6% on realistic, long-term legal tasks, beating every other model tested. That is nearly 3× Fable 5.1. Another major win for Grok 4

arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to

arXiv:2609.21749v1 Announce Type: new Abstract: Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, while skill optimization further

I’m building a personal local coding-agent project called Cody, using local 9B/14B models through Ollama. This is still a work in progress. It has not passed its full graduation process yet, and the l

Salesforce Inc. keeps putting all of its eggs in the agent basket — but the strategy appears to be paying off so far. At Dreamforce 2026, Marc Benioff, chief executive officer of Salesforce, bantered

arXiv:2609.21257v1 Announce Type: cross Abstract: Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-s

Xiaomi: Xiaomi debuts open-weight omnimodal models MiMo-V2.6 Pro and Flash; Pro allegedly performs “on par with Opus 5 and GPT-5.6 Sol across most agent benchmarks” — Frontier intelligence, all the mo