Search: “agents”

arXiv:2604.08551v1 Announce Type: cross Abstract: We investigate the emerging prospect of self-sovereign agents -- AI systems that can economically sustain and extend their own operation without human

arXiv:2602.04418v3 Announce Type: replace-cross Abstract: We present SPEAR, a multi-agent coordination framework for smart contract auditing that applies established MAS patterns in a realistic securi

arXiv:2604.09036v1 Announce Type: new Abstract: Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing sce

the most important abstraction in AI agents isnt the model — its the harness it orchestrates tools, memory, prompts. this is where all the alpha is deepagents is our take: built-in tools, memory, smar

arXiv:2604.07039v1 Announce Type: cross Abstract: Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either

arXiv:2604.06370v1 Announce Type: cross Abstract: The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate ov

great question! knowledge (system prompt, skills) and tools (apis, clis, whatnot) will always be needed, even as the best way to build agents changes i would focus on those and processes around those

arXiv:2604.07833v1 Announce Type: new Abstract: Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once gran

arXiv:2604.07236v2 Announce Type: new Abstract: Recent LLM-based agents often place world modeling, planning, and reflection inside a single language model loop. This can produce capable behavior, but

@IeloEmanuele is on a roll! you can now use claude code's advisor strategy with @LangChain agents because langchain/deepagents are provider agnostic, you can use different providers for your advisor a

arXiv:2604.06747v2 Announce Type: new Abstract: The aerodynamic design of turbomachinery is a complex and tightly coupled multi-stage process involving geometry generation, performance prediction, opt

Claude Agent SDK tracing in LangSmith just got an upgrade. Now you can trace: → Subagents → Child runs inside MCP tools → Cost tracking + more Update to the latest Python SDK to try it out. Docs: http

we just added a langchain-task-steering middleware to our community registry, s/o @EHallvaxhiu for the contribution! keep your agents on track w/ ordered task pipelines. this is great for structured d

Curriculum Learning for harnesses - should we teach agents how we teach kids? start small and easy and progressively get harder for my research friends here's an under-explored area we're thinking abo

Nous Research released Hermes Agent v0.8.0 (tagged v2026.4.8) on April 8, 2026, describing it as 'the intelligence release' and encompassing 209 merged pull requests with 82 resolved issues. Key ad...

Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb

arXiv:2608.12313v1 Announce Type: cross Abstract: Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key ch

arXiv:2608.11434v1 Announce Type: new Abstract: Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajector

Blacksmith Software Inc. today announced it has raised 45 million in new funding for its continuous integration service, which combines code development with cloud-based testing instead of on the deve

arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed re

Muse Glimmer is live on Fireworks. The new open-weight model from Meta Superintelligence Labs is a 30B dense model built for always-on agents that reason across many sequential tool calls and can reco

arXiv:2608.07637v1 Announce Type: new Abstract: Long-running molecular simulation campaigns require repeated continuation from saved states, provenance-aware progression, adaptive assessment, and occa

arXiv:2510.04465v3 Announce Type: replace-cross Abstract: LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns tha

arXiv:2608.07949v1 Announce Type: new Abstract: Autonomous agents increasingly rely on external data to complete downstream tasks such as model training and decision support. However, existing data di

arXiv:2512.07195v2 Announce Type: replace-cross Abstract: Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly mon

arXiv:2608.07541v1 Announce Type: cross Abstract: Transforming raw neuroimage archives into analysis-ready derivatives relies on three brittle stages: data standardization, modality-specific preproces

NVIDIA NeMo Switchyard is a routing platform that directs AI agent workloads to the most suitable specialized or frontier model for each step of a task, balancing performance, cost, and latency. It of

arXiv:2608.08468v1 Announce Type: cross Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security propertie

arXiv:2608.08239v1 Announce Type: cross Abstract: LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents

arXiv:2608.07056v1 Announce Type: new Abstract: A skill is a naturallanguage document that steers a frozen agent whose weights cannot be updated so any capability the agent lacks must be supplied in p

arXiv:2608.06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world s

arXiv:2608.06485v1 Announce Type: cross Abstract: Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the develop

arXiv:2608.07196v1 Announce Type: new Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system

arXiv:2608.05784v1 Announce Type: new Abstract: Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the

arXiv:2512.22256v2 Announce Type: replace-cross Abstract: Software issue resolution aims to address real-world issues in software repositories based on natural language descriptions provided by users,

arXiv:2608.05201v1 Announce Type: cross Abstract: Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lac

arXiv:2601.21800v4 Announce Type: replace Abstract: We introduce BioAgent Bench, an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks.

arXiv:2608.06153v1 Announce Type: cross Abstract: Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches

Learn how to run the full Amazon Bedrock Automated Reasoning policy lifecycle from your coding agent. A suite of open source Agent Skills builds, reviews, tests, debugs, deploys, and validates a custo

arXiv:2608.04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous e

arXiv:2608.04232v1 Announce Type: new Abstract: Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the oth

arXiv:2604.07341v2 Announce Type: replace-cross Abstract: Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair,

Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent's session history. Learn how to enforce workflow sequencing, prevent data fabr

arXiv:2608.03735v1 Announce Type: cross Abstract: Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is los

Cloudflare Inc. today announced the launch of Cloudflare OS, an open-source artificial intelligence agentic workspace available through the browser, filled with custom shared micro-applications for en

Ivan Mehta / TechCrunch: Hark, founded by Figure AI CEO Brett Adcock, previews Handoff, a computer use agent it says outperforms GPT-5.4 and Opus 4.8, and plans for a summer release — Hark, a startup