Knowledge catalogue
arXiv:2608.08621v1 Announce Type: new Abstract: Running a business is a challenging form of intelligent work. Operators must infer opportunities from partial signals, commit capital under uncertainty,
arXiv:2608.08570v1 Announce Type: new Abstract: Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining
arXiv:2608.07645v1 Announce Type: new Abstract: Self-improving coding agents that iteratively rewrite their own source code have demonstrated impressive performance on coding tasks. However, existing
arXiv:2608.07533v1 Announce Type: new Abstract: An embodied agent is an intelligent entity that interacts with its environment through a physical body. Currently, the evaluation of embodied agents pri
arXiv:2608.08939v1 Announce Type: new Abstract: The rise of autonomous AI agents represents a major paradigm shift in how users interact with mobile devices. Frameworks such as MobileRun and Mobile-Us
arXiv:2608.07437v1 Announce Type: new Abstract: Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate t
arXiv:2411.00028v3 Announce Type: replace-cross Abstract: Socioeconomic prediction aims to leverage various urban data to predict the socioeconomic indicators of regions such as population and commerc
arXiv:2608.06171v1 Announce Type: new Abstract: Web agents observe a browser through text, pixels, or both, and the choice is usually fixed once for all tasks. We measure six observation modes across
arXiv:2608.05884v1 Announce Type: cross Abstract: Existing guidance identifies excessive agency, excessive permission, weak task-bound authorization, and inadequate agent controls as important risks.
arXiv:2608.04934v1 Announce Type: new Abstract: Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with
ChatGPT Work is OpenAI's fighter in the highest stake product category in history: bringing the power of coding agents to the masses. It's also how a billion users will soon use ChatGPT by default. I
arXiv:2608.04003v1 Announce Type: new Abstract: Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for s
Exposure management startup ArmorCode Inc. today used Black Hat USA 2026 in Las Vegas to detail an expansion of its agentic artificial intelligence platform, adding four planned agents and three new s
arXiv:2608.01056v1 Announce Type: cross Abstract: Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments,
arXiv:2608.02101v1 Announce Type: new Abstract: Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning
arXiv:2512.06716v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as the core of agentic systems due to their strong reasoning, planning, and tool-use capabi
arXiv:2607.28651v1 Announce Type: cross Abstract: Collaboration supports learning and problem-solving, but its effectiveness depends on cognitive engagement during discourse. This study applies an ext
arXiv:2607.29468v1 Announce Type: new Abstract: Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gra
arXiv:2607.26072v1 Announce Type: cross Abstract: Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or pers
arXiv:2607.26314v1 Announce Type: cross Abstract: Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisti
arXiv:2607.27155v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support
arXiv:2607.27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental too
Signal, a managed agent built into Arize AX, continuously reviews production traces, surfaces ranked issues with evidence and proposed fixes, and — with Managed Agents — can carry investigations into
arXiv:2607.24167v1 Announce Type: new Abstract: Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, o
arXiv:2607.15557v4 Announce Type: replace Abstract: Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Pub
arXiv:2607.16900v2 Announce Type: replace Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale
arXiv:2607.13396v1 Announce Type: new Abstract: What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psyc
MODEL + GGUF : https://huggingface.co/InternScience/models?search=a1-4b Technical Report Benchmark Qwen3.5-4B Agents-A1-4B Qwen3.5 Qwen3.6 Nex-N2-mini Agents-A1 🧠 Dense Models (~4B) 🔀 MoE Models (35B-
arXiv:2306.02704v2 Announce Type: replace-cross Abstract: We introduce Calibrated Stackelberg Games (CSGs), a generalization of the standard Stackelberg Games (SGs) framework. In CSGs, a principal rep
arXiv:2607.08010v1 Announce Type: new Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference
Soak testing for AI agents involves running agents continuously over extended periods to identify performance degradation, resource leaks, stability issues, and edge cases that may not appear during s
arXiv:2607.05775v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and ope
arXiv:2607.03220v1 Announce Type: cross Abstract: Recent tools such as OpenClaw have extended the capabilities of LLM-based agents from simple dialog-based systems to fully autonomous agents. These sy
arXiv:2607.03821v1 Announce Type: cross Abstract: Personal AI agents that run on the user's local machine, such as OpenClaw, automate daily tasks including web search, email, and file management. Thei
arXiv:2607.05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the
arXiv:2607.04528v1 Announce Type: new Abstract: Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees
arXiv:2607.03695v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in interacting populations, raising the question of what such populations come to believe co
This post discusses using deep agents and OpenKeyFlow (OKF) for a wiki project built with LangGraph, a framework for constructing agent-based applications. The developer is leveraging LangGraph's capa
Can coding-agents replicate scientific ML papers? We know this is possible because we can already do this @dair_ai. Still a great read. So they try to replicate an ML paper from its materials alone. T
arXiv:2607.01584v1 Announce Type: new Abstract: Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-f
arXiv:2607.01236v1 Announce Type: cross Abstract: As LLM agents gain increasing access to powerful tools, ensuring that their actions are aligned with the user's intent becomes critical. When an agent
Agent evals are repeatable tests that score whether AI agents completed a task correctly. Learn how to design rubrics, test suites, and trace-based evals that catch failures and prevent reward hacking
LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of AI today. It's about being intentional in building and scalin
arXiv:2606.31564v1 Announce Type: new Abstract: The increasing complexity of agentic tasks has led to rapidly growing trajectory lengths, which poses significant challenges for large language model (L
arXiv:2606.30246v1 Announce Type: new Abstract: Existing autonomous research agents can support parts of the research process, but most systems still treat research as either an isolated assistant tas
arXiv:2606.29648v1 Announce Type: cross Abstract: Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understan
arXiv:2606.27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications. By operating a real device on the user's behalf, they reach far
arXiv:2506.12078v2 Announce Type: replace-cross Abstract: Understanding the dynamic evolution of complex social phenomena requires both high-fidelity modeling of human behavior and large-scale simulat
arXiv:2606.29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires con
Chris Metinko / Axios: Straiker, which develops tech for securing enterprise AI agents, raised a 64M Series A, bringing its total funding to 85M — Straiker, which secures AI agents, raised a $64 milli
Excited to see @cohere open-source how they use AI coding agents to maintain their vLLM fork. 🙌 Keeping a long-lived fork in sync is tricky. Their agent treats it as a control loop: rebase onto each u
What happens when AI agents collaborate on open science? At @aiDotEngineer World’s Fair, @james_y_zou will share work on EinsteinArena and DSGym, from multi-agent math discovery to better evaluation f
arXiv:2510.01299v3 Announce Type: replace-cross Abstract: We present domain-adapted large language model agents designed to support Cherenkov Telescope Array operation and data analysis. The agents co
arXiv:2602.11988v2 Announce Type: replace-cross Abstract: A widespread practice in software development is to tailor coding agents to repositories using context files, such as AGENTS.md. Although this
🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compute” or “dreaming” This involves running a background process to analyze agent trajectories and update a
arXiv:2506.04018v3 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents'
you need docs built for agents Docs are the eyes and ears of Agents. But we're moving so fast that they are always outdated. So hence an outdated doc also confuses the models. But it's also hard keep
arXiv:2606.11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may
Visa Inc. has struck a deal with OpenAI Group PBC to let artificial intelligence agents make payments for users, bringing one of the world’s largest payment networks into ChatGPT’s push toward agentic
arXiv:2605.22781v2 Announce Type: replace-cross Abstract: LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid chec