Knowledge catalogue
arXiv:2606.26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-h
arXiv:2606.25632v1 Announce Type: new Abstract: Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations. Yet long-narrative role-playing suff
arXiv:2606.25161v1 Announce Type: new Abstract: Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. E
arXiv:2606.16428v2 Announce Type: replace-cross Abstract: Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but al
arXiv:2606.24530v1 Announce Type: new Abstract: We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether
Jeremy Kahn / Fortune: Seltz, which is building a web search engine that can be used by AI agents, raised a $12.5M seed led by Speedinvest and B Capital — The rise of AI has rekindled the long-dormant
arXiv:2602.14257v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains
arXiv:2606.22948v1 Announce Type: cross Abstract: As multimodal agents move from interface understanding to real software control, successful trajectory discovery in live desktop environments becomes
arXiv:2606.20638v1 Announce Type: cross Abstract: Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes wi
arXiv:2606.20724v1 Announce Type: cross Abstract: Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate
GLM-5.2 represents a significant advancement in open-source AI agent capabilities, marking a notable improvement over previous versions in terms of performance and functionality. The article from Inte
There are basically two skillsets that matter more in the age of coding agents. The first is the one everyone talks about: product sense and taste. Code is cheap now, so knowing exactly what to build
arXiv:2606.12142v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, mos
arXiv:2606.12087v1 Announce Type: new Abstract: Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. E
arXiv:2606.11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. Whi
arXiv:2606.09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performan
arXiv:2602.04935v3 Announce Type: replace-cross Abstract: Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy t
arXiv:2606.05597v2 Announce Type: replace Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, a
Enterprise artificial intelligence context startup Jedify Inc. today announced that it has raised 24 million in new funding to build what it calls context graphs that give AI agents the business knowl
arXiv:2606.10616v1 Announce Type: new Abstract: Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts that exceed their finite context windows, making memory rete
Ram Iyer / TechCrunch: New York-based Jedify, whose platform connects to enterprises' knowledge sources via APIs to build a “context graph” for AI agents, raised a $24M Series A — AI vendors promote t
Paige Smith / Bloomberg: OpenAI and Visa partner to let AI agents make purchases online after users give their permission and to explore enterprise applications for AI-driven payments — OpenAI and Vis
arXiv:2606.09447v1 Announce Type: new Abstract: We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles. Major cloud platforms encomp
arXiv:2606.07837v1 Announce Type: cross Abstract: A concert is a collective experience, but recorded performance videos are typically watched alone, stripping away the shared audience presence that ma
Custom agents let GitHub Copilot CLI understand your stack and team workflows, turning one-off terminal prompts into repeatable, reviewable processes. The post From one-off prompts to workflows: How t
arXiv:2603.16020v2 Announce Type: replace Abstract: Adaptive agents operating under uncertainty must do more than optimize task outputs: they must maintain a workable internal state under noise, pertu
arXiv:2606.09483v1 Announce Type: cross Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal
arXiv:2601.19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they coo
arXiv:2606.08234v1 Announce Type: new Abstract: LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning
arXiv:2606.09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext in
arXiv:2606.09669v1 Announce Type: new Abstract: Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However,
arXiv:2606.07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking extern
arXiv:2602.08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unin
arXiv:2512.00883v3 Announce Type: replace-cross Abstract: World models simulate environmental dynamics to enable agents to plan and reason about future states. While existing approaches have primarily
Nous Research has released a feature or tool that allows users to display their AI agents in small, compact window sizes, improving UI flexibility and workspace management. This update addresses user
arXiv:2601.18510v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights a
arXiv:2606.06560v1 Announce Type: cross Abstract: Computer-use agents (CUAs) operate graphical user interfaces (GUIs) through vision and control primitives, and their capabilities have advanced rapidl
arXiv:2606.07027v1 Announce Type: new Abstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-le
arXiv:2606.05263v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chai
arXiv:2606.05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster
arXiv:2606.06087v1 Announce Type: new Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substa
arXiv:2606.05395v1 Announce Type: new Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior. We ar
arXiv:2407.03884v4 Announce Type: replace-cross Abstract: Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and
Endava, a software services company, is leveraging AI agents to fundamentally transform its software delivery processes and workflows. The case study likely demonstrates how the company is implementin
Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise work
NVIDIA's Nemotron 3 Ultra is a 550B-parameter Mixture-of-Experts model with 55B active parameters, optimized for orchestrating complex, long-running agent workflows by combining frontier reasoning and
arXiv:2606.04780v1 Announce Type: new Abstract: Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing age
arXiv:2606.04120v1 Announce Type: cross Abstract: Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions. However, simply expanding context win
arXiv:2606.03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The har
arXiv:2602.05302v3 Announce Type: replace Abstract: We present an in-depth evaluation of LLMs' ability to negotiate, a central business task requiring strategic reasoning, theory of mind, and economic
arXiv:2603.14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reason
arXiv:2606.00008v1 Announce Type: new Abstract: Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly const
Learn how Microsoft helps developers build trustworthy AI agents with open evaluations, portable runtime controls, production observability, and security workflows that work across frameworks. The pos
Data agents don't fail at writing SQL. They fail at knowing your business. Schemas show you the columns, but they don't tell you which view is canonical for ARR, how often each metric updates, or whic
arXiv:2606.01041v1 Announce Type: new Abstract: Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by integrating past interactions as reusable knowledge.
arXiv:2606.00644v1 Announce Type: new Abstract: AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be
arXiv:2606.02373v1 Announce Type: new Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which
arXiv:2606.01584v1 Announce Type: cross Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly
Microsoft Corp. today introduced Rayfin, an open-source software development kit and command-line interface that lets developers and coding agents define an entire application backend in code and depl
Michael Nuñez / VentureBeat: Microsoft unveils Microsoft Execution Containers for Windows, an OS-level sandbox for AI agents, with OpenAI, Nvidia, Manus, and Nous Research as partners — For the past t