Why AI agents might not be right for you
There’s no question that 2026 is the year of the artificial intelligence agent. AI agents are remarkably ubiquitous, as people use them to write code, communicate with customers, identify and resolve
Knowledge catalogue
There’s no question that 2026 is the year of the artificial intelligence agent. AI agents are remarkably ubiquitous, as people use them to write code, communicate with customers, identify and resolve
Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su
Reading eval results is now the slowest part of building agents. I'm Elvis, founder of @dair_ai. I lead research, build, and teach about AI agents. I run harness experiments every night, but reading t
arXiv:2609.34054v1 Announce Type: new Abstract: Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing s
arXiv:2609.31318v1 Announce Type: cross Abstract: AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adv
Deployment of agents can be halted at any moment. They are choosing to experiment with them. Agents are fundamentally unreliable, unpredictable, and insecure, not to mention the lack of information on
Runtime governance is becoming critical as autonomous agents move from answering questions to taking action across enterprise systems. Organizations need to govern both the business context agents rec
arXiv:2609.28416v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent
arXiv:2609.27490v1 Announce Type: new Abstract: AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding,
The domain name registrar company Identity Digital Inc. thinks it knows how to make artificial intelligence agents more accountable, and to do that it’s creating an entirely new company called Known S
This week we kicked off the DevFest season in North America at Google Hudson Square in New York City with 80 engineers packed into the room. Typical technical workshops hand you a finished repo, tell
arXiv:2609.19059v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) agents are increasingly used as personal assistants for long-running tasks. Their utility depends on continuity
Why does the AI industry wants you to believe in “rogue agents” when we are really just talking about irresponsibly developed software? Here’s a good theory: @haydenfield @mmitchell_ai @HeidyKhlaaf @t
At Orange, the leading France-based multinational telecom provider, there are days when engineering teams set aside their delivery backlogs and spend the day cleaning up cloud spend together. There's
If you build agent harnesses, this is important. Should you avoid subagents, or can they be useful? My thoughts as a harness builder: I remember using subagents in Claude Code, and I mostly found them
arXiv:2609.13491v1 Announce Type: new Abstract: The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the
arXiv:2609.11018v1 Announce Type: new Abstract: The term agent in artificial intelligence lacks a standard definition, complicating the evaluation, comparison, and reproducibility of AI agent research
arXiv:2609.11677v1 Announce Type: cross Abstract: Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for o
arXiv:2408.02920v2 Announce Type: replace-cross Abstract: The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detai
arXiv:2609.09754v1 Announce Type: new Abstract: As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning e
arXiv:2609.06815v1 Announce Type: cross Abstract: An open, networked web will allow agents to run frozen models from multiple vendors, keep their history private, and teach each other which tool to ca
This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase the underlying work history. In Deep Agents, the logic is: -
arXiv:2609.01779v1 Announce Type: cross Abstract: Future 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN). However, current architectures assume inte
arXiv:2606.19319v2 Announce Type: replace-cross Abstract: Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively
arXiv:2608.27856v1 Announce Type: new Abstract: Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling
arXiv:2608.24099v1 Announce Type: new Abstract: GUI agents often encounter dynamic anomalies when deployed on Android devices, from unexpected pop-ups to action misuse, yet existing benchmarks lack sy
arXiv:2608.24017v1 Announce Type: cross Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent
Have you been hearing a lot about 'AI agents' lately but aren't sure how to actually start building them? You don't need a background in machine learning or years of software experience to get started
arXiv:2608.21101v1 Announce Type: cross Abstract: As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent h
arXiv:2608.20274v1 Announce Type: new Abstract: Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced
arXiv:2608.18066v1 Announce Type: new Abstract: Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have sho
arXiv:2608.10037v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical groundin
arXiv:2608.10716v1 Announce Type: cross Abstract: Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing
the @aiDotEngineer World Fair always one of the best events every year to talk to builders at the frontier of Research, Agents, Evals, Systems, etc A few weeks ago I gave a talk on - Continually Impro
arXiv:2607.18171v2 Announce Type: replace Abstract: Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose effici
arXiv:2608.05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patc
arXiv:2608.01042v1 Announce Type: cross Abstract: Enterprise AI agents act across many apps whose data changes continuously, so an answer is correct only relative to what data existed and who could se
Impressive paper! It's on one of the hardest tasks for coding agents today. Of course, I am talking about kernel optimization. Coding agents are usually not so great at this. Reasons: Unfamiliar low-l
arXiv:2607.24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynam
arXiv:2607.13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, acti
arXiv:2606.20950v2 Announce Type: replace Abstract: Executable evaluation -- checking the consequences of an agent's actions with a program rather than grading its prose -- has become a prominent way
arXiv:2606.28456v1 Announce Type: cross Abstract: LLMs agents are increasingly used in multi-agent settings, yet their behaviour in sustainability games remains largely unexplored. This work investiga
arXiv:2606.28450v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial
Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that increasi
To defend against the growing range of AI-accelerated threat actors, organizations need to be able to respond faster to outpace the adversary.Recently, we announced Google AI Threat Defense, an automa
Outstanding paper on long-horizon agents. (bookmark it) Similar to humans, how do you make agents persist on a difficult task, and how is that useful? And which models today work well on this? This ne
Skill issue: Lessons from skilling up coding agents Getting agents to actually use Langfuse was a 'skill issue' — literally. Marc Klingen from Clickhouse on teaching coding agents to use new tools, an
arXiv:2606.03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model ca
Big paper on AI coding agents using Github & other data The auto-complete tools (Copilot) led to 2.2x more code, local agents like original Claude Code led to 7.4x, & current remote coding agents 17.3
Very good advice on self-improving agents. (bookmark it) This is something I am seeing in my own experiments with coding agents and harnesses for long-horizon tasks. What I have found is that stronger
arXiv:2605.29174v1 Announce Type: new Abstract: DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 20
arXiv:2605.18652v1 Announce Type: new Abstract: Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require m
arXiv:2605.08693v1 Announce Type: new Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selec
arXiv:2603.25719v2 Announce Type: replace-cross Abstract: We present an empirical study of how far general-purpose coding agents -- without hardware-specific training -- can optimize hardware designs
As we have built our own harness management tools internally at Arize, and watched external systems like Devin @cognition start managing other Devins, managed agents at @AnthropicAI and long running T
agents are going and are already changing every industry & vertical, awesome blog from the @MadrigalPharma team on using Deep Agents, Skills, & LangSmith at the frontier of biopharma it’s an awesome t
Proactive agent that thinks and acts like you. Multiplayer AI Brain for teams. Proper GUI for commanding 50 agents. http://Sauna.ai is all three. Sauna goes live today. First 2000 people, use access c
Business process automation software company Appian Inc. is stepping up its game in agentic artificial intelligence, announcing major updates to its platform focused on AI-assisted application develop
arXiv:2604.22820v1 Announce Type: cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibil
Lately I've been having fun with running coding agents fully locally. The setup I landed on is: - Pi agent - Gemma 4 26B A4B - Server of choice: LM Studio/Ollama/llama.cpp I wrote a step-by-step guide