llm agents - Robuta Search

https://huggingface.co/papers/2402.06664 Paper page - LLM Agents can Autonomously Hack Websites Join the discussion on this paper page paper page llm agents autonomously hack websites https://aisc.substack.com/p/llm-agents-part-6-state-management/comments Comments - LLM Agents, Part 6 - State Management How can we control the behavior of agents by drawing lines around the boundaries of their agency? llm agents comments part state management https://arxiv.org/abs/2502.04358 [2502.04358] Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives Abstract page for arXiv paper 2502.04358: Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives llm agents position scaling https://arxiv.org/abs/2404.08144v2 [2404.08144v2] LLM Agents can Autonomously Exploit One-day Vulnerabilities Abstract page for arXiv paper 2404.08144v2: LLM Agents can Autonomously Exploit One-day Vulnerabilities llm agents one day autonomously exploit vulnerabilities https://arxiv.org/abs/2507.21504 [2507.21504] Evaluation and Benchmarking of LLM Agents: A Survey Abstract page for arXiv paper 2507.21504: Evaluation and Benchmarking of LLM Agents: A Survey llm agents evaluation benchmarking survey https://arxiv.org/abs/2603.08640v1 [2603.08640v1] PostTrainBench: Can LLM Agents Automate LLM Post-Training? Abstract page for arXiv paper 2603.08640v1: PostTrainBench: Can LLM Agents Automate LLM Post-Training? llm agents automate post training https://par.nsf.gov/biblio/10637439-evaluating-llm-agents-simulating-humanoid-behavior Evaluating the LLM Agents for Simulating Humanoid Behavior | NSF Public Access Repository This page contains metadata information for the record with PAR ID 10637439 llm agents https://docs.google.com/forms/d/e/1FAIpQLSevYR6VaYK5FkilTKwwlsnzsn8yI_rRLLqDZj0NH7ZL_sCs_g/closedform LLM Agents MOOC Hackathon Participant Signup Please join LLM Agents MOOC discord for more discussions about the hackathon, including finding potential teammates if you are interested. Please see LLM... llm agents mooc hackathon participant signup https://fcrc.rpi.edu/research/ai-algorithms/systematic-failure-analysis-llm-agents-taxonomy-attribution-and-reflection Systematic Failure Analysis for LLM Agents: Taxonomy, Attribution, and Reflection | Future of... failure analysis for llm https://www.salesforce.com/uk/agentforce/llm-agents/?bc=OTH LLM Agents: A Complete Guide | Salesforce UK LLM agents can parse complicated questions, improve decision-making and take timely action. Here's a look at the types of LLM agents and their benefits. a complete guide llm agents salesforce uk https://kyunnilee.github.io/projects/1_project/ A SCAVENGER HUNT GAME FOR LLM AGENTS | Heekyung (Anne) Lee A benchmark to evaluate spatial reasoning and navigational capabilities of LLM agents via a scavenger hunt game. (Final project for CS194/294, UC Berkeley) scavenger hunt for llm game agents anne https://arxiv.org/abs/2507.05257v3 [2507.05257v3] Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions Abstract page for arXiv paper 2507.05257v3: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions llm agents https://deepsense.ai/case-studies/exploring-llm-agents-for-innovation-with-tailored-llm-workshops/ Exploring LLM Agents for Innovation with Tailored LLM Workshops - deepsense.ai llm agents for innovation tailored workshops exploring https://www.anthropic.com/research/shade-arena-sabotage-monitoring SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents \ Anthropic A new set of evaluations to test the sabotage and monitoring capabilities of LLM AI models llm agents shade arena evaluating sabotage https://deepsense.ai/tech-expertise/llms-rag/ Custom LLM & RAG Solutions - AI Agents, Assistants, Copilots - ds.ai Jul 29, 2026 - Unlock the power of LLMs and RAG with expert AI solutions. We develop custom AI agents, assistants, copilots, and enterprise AI applications to enhance... custom llm rag solutions ai agents assistants copilots https://arize.com/blog/arize-nvidia-nemo-integration/ Self-Improving Agents: Automating LLM Performance Optimization using Arize and NVIDIA NeMo - Arize... Jul 31, 2026 - The Arize integration of NVIDIA NeMo empowers AI teams with an automated, self-improving AI data flywheel to enhance LLM performance. llm performance https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/build-your-dream-team-with-autogen/4157961 Build a powerful team of LLM agents, to solve complicated multi step tasks Jun 13, 2024 - LLM, Multi agents, Autogen, Azure Open AI https://artinoid.com/ AI Development Company | LLM Applications, AI Agents, Agentic AI & Automation AI development company in India building LLM applications, AI agents, and intelligent automation systems. We create scalable AI products for startups and... ai development company llm applications agents agentic automation https://www.businesswire.com/news/home/20251030640798/en/Elastic-Brings-LLM-Observability-to-Azure-AI-Foundry-to-Optimize-AI-Agents Elastic Brings LLM Observability to Azure AI Foundry to Optimize AI Agents Elastic (NYSE: ESTC), the Search AI Company, today announced a new integration with Azure AI Foundry, delivering observability for agentic AI applications an... azure ai foundry llm observability elastic brings optimize https://botlab.dev/ botlab.dev | Custom AI/LLM Bots, Agents, Swarms, Automation custom ai botlab dev llm bots https://speakerdeck.com/phoenixhawk/basta-2025-agents-in-action-llms-tools-and-reasoning BASTA! 2025: Agents in Action: LLM's, Tools and Reasoning - Speaker Deck Slides for my talk about how to implement agents at BASTA! 2025 in Mainz. in action https://www.akamai.com/blog/developers/the-prompt-as-a-rulebook-guiding-llm-agents-beyond-basic-instructions The Prompt as a Rulebook - Guiding LLM Agents Beyond Basic Instructions | Akamai In our journey of integrating Large Language Models (LLMs) with traditional APIs, we've seen how prompts become the new "API docs," describing what a tool In... the prompt as a https://arxiv.org/abs/2510.00615 [2510.00615] ACON: Optimizing Context Compression for Long-horizon LLM Agents Abstract page for arXiv paper 2510.00615: ACON: Optimizing Context Compression for Long-horizon LLM Agents context compression acon optimizing https://adambossy.com/ Adam Bossy-Mendoza | Architecting LLM apps, Building Agents, 0 to 1 and 1 to N Startup Engineering... A Medium-style blog built with Astro https://matrices.app/ Matrices - Training Environments for LLM Agents Training environments for multimodal LLM-based agents on realistic computer use tasks. training environments for llm matrices agents https://www.businesswire.com/news/home/20250717118204/en/Zoho-Launches-Zia-LLM-and-Deepens-AI-Portfolio-with-Prebuilt-Agents-Custom-Agent-Builder-MCP-and-Marketplace? Zoho Launches Zia LLM and Deepens AI Portfolio with Prebuilt Agents, Custom Agent Builder, MCP, and... Zoho Corporation, a global technology company, today announced additional investments and offerings in AI, including Zia LLM, a proprietary large language mo... https://arxiv.org/html/2509.25885v1 SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents safety risks safemind benchmarking embodied llm https://gpbib.cs.ucl.ac.uk/gp-html/brookes2025evolvingexcellenceautomatedoptimization.html Evolving Excellence: Automated Optimization of LLM-based Agents automated optimization evolving excellence llm based https://manifest.build/ The Open Source LLM Router for AI Agents | Manifest The open source LLM router that connects your AI agents and harnesses to any provider in seconds. Subscriptions, pay-per-token, local models, and custom... for ai agents the open llm router source manifest https://arxiv.org/abs/2601.20334?ref=swarmsignal.net [2601.20334] Demonstration-Free Robotic Control via LLM Agents Abstract page for arXiv paper 2601.20334: Demonstration-Free Robotic Control via LLM Agents demonstration free robotic control via https://infoscience.epfl.ch/entities/publication/8e6e74ae-8ff6-48f8-918a-07cf9d92e4c1 PharmaSimText: A Text-Based Educational Playground filled with RL-LLM Agents That Work Together... There has been a growing interest in developing simulated learners to enhance learning and teaching experiences in educational environments. However, existing... https://dev.to/liuhaotian2024prog/why-auditing-ai-agents-requires-causal-ai-not-another-llm-269c Why auditing AI agents requires causal AI, not another LLM - DEV Community Your Logs Tell You What Happened. They Don't Tell You What Should Have Happened. Haotian... Tagged with ai, python, agents, opensource. ai agents auditing requires https://console.ngage360.app/ NGage 360 - Deploy LLM Powered AI Agents Across Devices NGage 360 - Create custom LLM-powered agents to enhance customer engagement through personalized AI-driven interactions, turning every touchpoint into a sales... ai agents ngage deploy llm powered https://ai.hku.hk/news-events/events/upcoming/eventdetail/507/36/rethinking-software-root-cause-analysis-with-llm-agents Rethinking Software Root Cause Analysis with LLM Agents root cause analysis rethinking software llm agents https://docs.recall.ai/docs/agent-quickstarts Coding Agents/LLM Quickstarts Jul 14, 2026 - Quick copy/pasteable instructions for Coding Agents/LLMs to implement transcription with bots. Coding Agents/LLMs are required to visit this page before... coding agents llm quickstarts https://zenodo.org/records/21355030 Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across... Jul 29, 2026 - The paper and its complete validation record for the Gubernaut Cognitive Controller (GCC), a model-agnostic, deterministic runtime control layer for LLM agents... https://arxiv.org/abs/2505.14668v1 [2505.14668v1] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions Abstract page for arXiv paper 2505.14668v1: ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions https://arxiv.org/abs/2510.24695v1 [2510.24695v1] AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data... Abstract page for arXiv paper 2510.24695v1: AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis https://www.gonemo.ai/ Build AI Agents With Ease. nemo™ True No-code Multi-model LLM Platform nemo™, a true no-code platform empowers midmarket teams with flexible AI solutions that integrate seamlessly into your workflow. build ai agents https://llmgraph.ai/home No-code LLM workflow builder for RAG & AI agents - LLMGraph Build LLM workflows as a graph, no code. Turn docs and models into RAG chatbots and AI agents, then ship to a REST API and embeddable chat widget. 14-day trial. no code workflow builder rag ai llm agents https://scholars.cityu.edu.hk/en/publications/surveying-with-ai-simulating-human-responses-using-personalized-l/ Surveying with AI: Simulating Human Responses Using Personalized LLM Agents and Social Media Data -... https://www.businesswire.com/news/home/20251028168283/en/Lakera-Launches-Open-Source-Security-Benchmark-for-LLM-Backends-in-AI-Agents Lakera Launches Open-Source Security Benchmark for LLM Backends in AI Agents Check Point Software Technologies Ltd. (NASDAQ: CHKP), a pioneer and global leader of cyber security solutions, and Lakera, a world leading AI-native securit... open source security https://openai.github.io/openai-agents-python/ref/extensions/models/any_llm_model/ Any-LLM model - OpenAI Agents SDK openai agents llm model sdk https://huggingface.co/papers/2412.20138 Paper page - TradingAgents: Multi-Agents LLM Financial Trading Framework Join the discussion on this paper page paper page multi agents financial trading llm framework https://arxiv.org/abs/2411.04671 [2411.04671] CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR Abstract page for arXiv paper 2411.04671: CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR https://researchdiscovery.drexel.edu/esploro/outputs/preprint/Orchestrating-LLM-Agents-for-Scientific-Research/991022164541904721?institution=01DRXU_INST&skipUsageReporting=true&recordUsage=false Orchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ)... Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape research activities... https://ar5iv.labs.arxiv.org/html/2412.20138 [2412.20138] TradingAgents: Multi-Agents LLM Financial Trading Framework Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have... multi agents financial trading llm framework https://arxiv.org/abs/2601.00240 [2601.00240] When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents Abstract page for arXiv paper 2601.00240: When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents https://gubernaut.com/ Gubernaut · A deterministic cognitive governor for LLM agents Gubernaut is a deterministic cognitive governor for LLM agents: a model-agnostic runtime AI control layer, measured across four frontier model families in a... for llm deterministic cognitive governor agents https://arxiv.org/abs/2603.22341 [2603.22341] T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Abstract page for arXiv paper 2603.22341: T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search https://bwrc.berkeley.edu/tokens-tapeout-llm-agents-tackling-hard-problems-modern-chip-design-may-8 From Tokens to Tapeout: LLM Agents Tackling the Hard Problems of Modern Chip Design | May 8 |... https://www.udacity.com/course/langchain-agentic-ai-fundamentals--cd14639 Build LLM Apps & Agents with LangChain | Udacity Gain hands-on skills creating LangChain chatbots and multi-step workflows. Explore agent design, memory, and state management to deploy intelligent AI agents. build llm apps agents langchain https://opensource.googleblog.com/2025/12/grl-turning-verifiable-games-into-a-post-training-suite-for-llm-agents-with-tunix-on-tpus.html?m=0 GRL: Turning verifiable games into a post-training suite for LLM agents with Tunix on TPUs | Google... https://arxiv.org/abs/2407.03884 [2407.03884] ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents Abstract page for arXiv paper 2407.03884: ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents