agents

https://x.com/walden_yan/status/2052070983083942322?s=20 Cool to see failure modes of different coding agents in new report from @greptile - seems like Devin is better than humans in almost all catego

arXiv:2605.02682v1 Announce Type: new Abstract: Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, a

i have nothing against companies selling data if they are upfront about it, but this messaging feels a bit misleading: 'AI shouldn’t replace you. It should make you irreplaceable.' When their terms of

I was talking with @josephruscio on the @heavybit podcast the other day when I realized that vibe coding and agentic engineering have started to blur a bit in some of my work - I published some extrac

arXiv:2511.20657v2 Announce Type: replace-cross Abstract: The development of agents with emotional intelligence is becoming increasingly vital due to their significant role in human-computer interacti

It's time to build NYC's physical AI community. We're hosting a small dinner in NYC for engineers and people building across robotics, autonomous systems, and world models. It's a pretty unique and sp

Last week I gave a talk at AI Dev ’26 by @DeepLearningAI on “AI can’t read PDFs, how do we fix it” . I’m sharing the slides publicly if others are interested in doing a deep dive into document underst

arXiv:2605.01694v1 Announce Type: new Abstract: A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and suppor

arXiv:2601.21972v4 Announce Type: replace Abstract: Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL). However, most MARL fine-tuning approaches r

arXiv:2605.01610v1 Announce Type: cross Abstract: AI systems have long been expected to interact with users, answering questions, generating content, and continuing (social) conversations. Agentic AI,

arXiv:2605.01293v1 Announce Type: new Abstract: Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing

arXiv:2605.02335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communi

arXiv:2505.16120v2 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered

arXiv:2507.15143v3 Announce Type: replace Abstract: This paper investigates the feasibility of human mobility in extreme urban morphologies characterized by high-density vertical structures and linear

arXiv:2605.03288v1 Announce Type: new Abstract: Many physical AI tasks are governed by implicit equilibrium: an agent actuates a subset of degrees of freedom (boundary DoFs), while the remaining free

arXiv:2605.04036v1 Announce Type: cross Abstract: Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominat

People love to ask what they can use Hermes Agent for. Hermes scraped the internet for answers and added them to our docs as inspiration. And if you've found an interesting use case, you can submit yo

Consumer-focused artificial intelligence startup PineAI, the business name of 19Pine Pte. Ltd., has launched an agentic AI service designed to handle time-consuming customer service interactions on be

arXiv:2605.01471v1 Announce Type: cross Abstract: Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study o

arXiv:2605.02940v1 Announce Type: new Abstract: The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation.

arXiv:2605.01865v1 Announce Type: cross Abstract: Cooperative multi-agent reinforcement learning (MARL) requires agents to discover joint strategies in a combinatorially large state-action space, yet

arXiv:2605.03863v1 Announce Type: cross Abstract: The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well establi

arXiv:2605.03260v1 Announce Type: new Abstract: Model Predictive Path Integral (MPPI) control is a powerful sampling-based strategy for nonlinear autonomous systems. However, its performance is often

arXiv:2605.01783v1 Announce Type: new Abstract: Procedural Content Generation (PCG) enables game content to be created algorithmically without direct manual level-design effort, but it introduces a se

arXiv:2605.03244v1 Announce Type: new Abstract: Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level

arXiv:2605.03788v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time

arXiv:2602.03548v3 Announce Type: replace Abstract: Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in

Security training platform startup Herd Security Inc. today announced that it has raised 3 million in new funding to expand product development across new training categories in human resources and ar

arXiv:2605.00827v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP).

arXiv:2605.01879v1 Announce Type: new Abstract: The challenge of engineering autonomous agents capable of navigating the stochastic and adversarial nature of the physical world has historically reside

small workflow note that adds up. /staged-pr is a skill (via slash command) i run when wrapping up a PR. it takes my staged code changes and drafts a concise PR title & description, based on my prefer

arXiv:2605.03842v1 Announce Type: cross Abstract: Robotic Mobile Fulfillment Systems (RMFS) rely on mobile robots for automated inventory transportation, coordinating order allocation and robot schedu

Stop token maxxing 🛑 Our CEO @ashashutosh sat down with @a16z General Partner Peter Levine to discuss why we’re moving beyond the vector database: '85% of an agent’s work isn't the model; it's the und

SWE-Check is live in Windsurf! So fun to collaborate with @cognition to post-train this. Try it out! Devin Review runs hundreds of thousands of times per day. Starting today, run it directly from Wind

arXiv:2605.03125v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) holds great potential but faces robustness challenges due to environmental uncertainty. To address this, distr

Cybersecurity software provider Tanium Inc. today announced a new partnership with ServiceNow Inc. to deliver a joint autonomous information technology solution, ITOM AI Prime powered by Tanium. The j

arXiv:2605.02244v1 Announce Type: cross Abstract: Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-ho

the deeper point: model choice and harness choice aren't independent variables. benchmarking a model without specifying the harness is like benchmarking a chip without specifying the compiler. the num

arXiv:2511.14887v2 Announce Type: replace Abstract: The rapid advancement of electric vertical takeoff and landing (eVTOL) aircraft offers a promising opportunity to alleviate urban traffic congestion

arXiv:2605.01329v1 Announce Type: new Abstract: In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social coope

How to build the “Trust Layer” for Github Copilot Coding Agents without brittle scripts or black-box judgements by using dominatory analysis. The post Validating agentic behavior when “correct” isn’t

arXiv:2603.28489v2 Announce Type: cross Abstract: The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as pot

We have greatly expanded the surface area for plugins over the last few weeks, and now you can extend LLM Inference Providers and Gateway Channels with plugins. Want a custom implementation of your fa

Harrison Chase expresses support for expanding AI benchmarking efforts and highlights appreciation for work being done by Harvey (likely Harvey AI, a legal AI company). The post indicates enthusiasm f

We're launching the agentic robotics app store today. Let's democratize AI robotics for all! 300+ apps shipped. 10,000 robots in the wild. It used to take weeks from a robotics engineer to build apps,

Open hybrid cloud is becoming the control plane that determines how enterprise artificial intelligence actually runs in production. The conversation has moved quickly from experimentation to execution