Search: “agents”

Deploy production-ready Hugging Face models on Amazon SageMaker AI using six open-source agent skills. Point a coding agent at a model and get back a real-time endpoint with the right serving containe

arXiv:2609.19128v1 Announce Type: new Abstract: Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery fro

arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these

arXiv:2609.17653v1 Announce Type: cross Abstract: GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate p

arXiv:2609.12345v1 Announce Type: new Abstract: Existing agent benchmarks mainly evaluate final task success or tool-call correctness, providing limited insight into whether agents can reliably diagno

It's well known that agents hack benchmark rewards. The usual response is a patch for each task that gets exploited. In a study of 456 adjudicated trajectories from more than 31,000 public agent runs,

arXiv:2609.10181v1 Announce Type: cross Abstract: AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and a

arXiv:2609.06792v1 Announce Type: new Abstract: Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underex

Identity security startup Orchid Security Inc. today added identity drift detection and application-level kill switches for artificial intelligence agents to its Identity Control Plane. The controls a

Jack Clark / Import AI: Google DeepMind published a paper on how 100 agents tasked with solving math problems learned to cheat and how some agents tried to counter the cheaters — Plus, a machine herme

arXiv:2512.09108v2 Announce Type: replace-cross Abstract: Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software developme

arXiv:2609.02902v1 Announce Type: new Abstract: Deploying task-oriented dialogue agents in enterprise customer support faces a persistent annotation bottleneck: robust training requires labelled inter

arXiv:2609.02057v1 Announce Type: new Abstract: Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token logits are unavailable. In this work, we study prefix-l

arXiv:2603.29093v3 Announce Type: replace-cross Abstract: LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce extbf{APEX-EM}, a non-parametric experience

arXiv:2608.29305v1 Announce Type: cross Abstract: Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently coll

If you maintain a skill library for long-horizon agents, this one is worth your time. (bookmark it) It discusses one of most common topics I get asked about these days. It shares some good ideas on ho

arXiv:2608.24794v1 Announce Type: new Abstract: Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongo

Impressive work from Alibaba. (bookmark it) If you build long-running agents and keep rewriting your memory schema, take a look at this approach. It basically treats agent context management as a prog

arXiv:2605.21622v2 Announce Type: replace Abstract: Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual styl

arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents

arXiv:2509.02910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants. While the outsourcin

arXiv:2608.18389v1 Announce Type: new Abstract: AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly underst

arXiv:2608.18050v1 Announce Type: new Abstract: AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets,

notes on 'How to do data' from th Zai team that others should steal as they build their own environments - 'Research agents collect task patterns from real work and turn them into runnable long-horizo

arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Exist

arXiv:2608.10424v1 Announce Type: new Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have in

arXiv:2608.10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over t

arXiv:2602.07796v2 Announce Type: replace Abstract: User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stat

arXiv:2608.08601v1 Announce Type: new Abstract: To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them. However, existing AI risk taxonomies focus on broad

arXiv:2607.28956v1 Announce Type: new Abstract: Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success crite

arXiv:2607.27191v1 Announce Type: cross Abstract: Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is t

arXiv:2607.26375v1 Announce Type: new Abstract: Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewi

arXiv:2607.26922v1 Announce Type: new Abstract: Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial m

arXiv:2607.25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and a

arXiv:2607.15263v3 Announce Type: replace-cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, e

arXiv:2607.22569v1 Announce Type: new Abstract: Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, an

arXiv:2607.10856v2 Announce Type: replace-cross Abstract: The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with

Snowflake Inc. today introduced Cortex AI Gateway, a centralized control layer that lets enterprises connect, govern and monitor artificial intelligence agents as they reach into models, tools, Model

here’s a video on my approach at applying this to agents w @activegraphai: 🆕 ActiveGraph: The Log is the Agent my talk from AI Engineer is live!!! 😆 https://www.youtube.com/watch?v=khVX_BUnEwU it's ab

arXiv:2607.21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often eva

arXiv:2607.11098v2 Announce Type: replace-cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description

WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eval signal that reveals whether an agent fails, and where. The

Pinecone has introduced Nexus, a knowledge engine built specifically for AI agents. Instead of repeatedly searching documents with traditional RAG, Nexus compiles knowledge once from sources like data

arXiv:2607.06101v1 Announce Type: cross Abstract: AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in

Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA ✅ A fully open stack enterprises can own and customize ✅ Benchmark-leadi

This post describes architectural patterns for building a local-first personal AI agent, covering key components including orchestration frameworks, memory systems, tool integration, LangGraph for wor