Knowledge catalogue
arXiv:2607.05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first
arXiv:2607.06341v1 Announce Type: cross Abstract: Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers
My team talks directly to *my* AI workforce. They can skip me entirely. It's the first time working with AI agents actually feels team-oriented and collaborative (and not just one person becoming more
Prime Intellect raises $130M Series A to help enterprises build their own AI agents https://techcrunch.com/2026/07/08/prime-intellect-raises-130m-series-a-to-help-enterprises-build-their-own-ai-agents
To audit SWE-Bench Pro, we used model-based investigator agents alongside independent reviews from five independent experienced software engineers. That helped us examine tasks at scale while keeping
arXiv:2607.03525v1 Announce Type: cross Abstract: Game engines provide real-time simulation, rendering, physics, interaction, networking, and asset pipelines, making them valuable not only for games b
The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories fo
As working with AI agents looks more like management, we may want to consider large-scale management training for the AI era. The US government actually did this once, & the WW2 Engineering, Science,
Wency Chen / South China Morning Post: ByteDance's Doubao and Alibaba's Qwen will disable humanlike and user-created agents before July 15, as China's anthropomorphic AI interaction rules take effect
Multimodal prompting enhances coding agents by enabling them to process and integrate multiple types of input data—such as text, images, and code snippets—simultaneously, improving their ability to un
This post discusses the evolution of multimodal prompting in AI agent interactions, highlighting how users can now communicate with AI systems using multiple input types beyond text. The author provid
Samantha Elkins / NBC News: Cloudflare sets a September 15 deadline for AI companies to differentiate their web crawlers into search, AI training, and AI agents or face being blocked — Cloudflare gave
Hot take: I think it's still important to understand the code that our agents write! In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how t
The Information: Memo: Microsoft is merging the consumer and enterprise versions of its Copilot chatbots into a single app featuring coding tools and AI agents dubbed AutoPilot — Microsoft is merging
arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in a
arXiv:2607.00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produce
good post on the value of knowing whats going on in your harness 'For agents within an actual product, I have gravitated to using LangChain DeepAgents' The frontier model lab harnesses are amazing - d
arXiv:2606.31045v1 Announce Type: new Abstract: Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory e
Our research team has 9 papers at ICML next week! Spanning the full stack from frontier agents to GPU kernels, we're excited to share what our researchers and collaborators have been working on. If yo
arXiv:2606.31154v1 Announce Type: cross Abstract: Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for
arXiv:2606.32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-onl
arXiv:2606.28430v1 Announce Type: cross Abstract: Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity proble
Stephanie Stacey / Financial Times: Hotels, tour operators, and travel agencies rush to launch proprietary online tools and loyalty schemes to fend off future competition from AI travel agents — Chatb
arXiv:2606.16364v2 Announce Type: replace Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness. We show the opposite through a
arXiv:2606.29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to
Our Founder and Chief Scientist @EdoLiberty just kicked off the Search & Retrieval track @aiDotEngineer. 'Agents don't need to be smarter. They need a Knowledge Layer.' We've got a big update on this
ScarfBench is a benchmarking framework designed to evaluate AI agents' capabilities in migrating enterprise Java applications to modern frameworks. The benchmark likely assesses how well AI systems ca
We’re introducing GeneBench-Pro, a research-level benchmark for a harder kind of AI progress: how well agents can navigate messy biological data, choose the right analysis path, and make judgment call
arXiv:2606.28376v1 Announce Type: cross Abstract: Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memor
arXiv:2606.27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillati
arXiv:2606.16682v3 Announce Type: replace-cross Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge. We show that Evaluator Preferen
this has to be because coding agents change the engineering math on how it is to work with or port a legacy codebase, right? anyone at Riot able to confirm? League of Legends Classic is coming as a ne
Vercel has launched voice agent capabilities on its AI Gateway platform, enabling developers to build real-time applications with speech and transcription features. The announcement indicates new inte
I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab
arXiv:2606.26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key sourc
arXiv:2606.27025v1 Announce Type: new Abstract: Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant par
arXiv:2606.26806v1 Announce Type: new Abstract: Long-running language agents need more than memory access. Retrieval systems can fetch past facts at query time, but they do not decide which experience
arXiv:2602.08995v2 Announce Type: replace Abstract: Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from th
arXiv:2606.27288v1 Announce Type: new Abstract: Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain
arXiv:2606.26935v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown that verbalized CoT is not always faithful and may in
Rebecca Bellan / TechCrunch: General Intuition, which trains AI agents in spatial reasoning via gameplay footage, raised 320M led by Khosla at a 2.3B valuation, for $454M in total funding — As soon as
Zac Hall / 9to5Mac: Notion plans to shut down its Gmail client Notion Mail on September 22 and go “all in” on AI agents to run inboxes, saying 50%+ of users do not open the inbox — Last year, Notion e
arXiv:2606.25852v1 Announce Type: new Abstract: Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajector
3/3 We took 7 weak agents (ranks 7-13, none scoring >45) from the leaderboard & merged them into 1 report/task. Essentially boosting for deep research. The result: New #1 DRB II TotalScore of 64.38. F
arXiv:2606.24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains lab
Jagmeet Singh / TechCrunch: Customer engagement service MoEngage acquires Aampe, whose AI agents help brands personalize messaging, for “tens of millions”, per a source; Aampe raised ~$28M — Indian cu
David Cendon Garcia / EU-Startups: London-based Isometric, which develops AI agents that work with human verifiers to automate industrial certification, raised a €34M Series A led by AVP — Isometric h
Lily Mae Lazarus / Fortune: Runlayer, which provides an infrastructure and control layer for enterprise AI agents, raised a 30M Series A led by Felicis, bringing its total funding to 42M — When longti
Brock E.W. Turner / Axios: Trase, which is building an operating system and infrastructure layer for AI agents in industries like health care and defense, raised a 107M seed led by Arch — Trase, an AI
Claude Tag is an incredible new form factor for agents, so I think it's going to take some time to figure out the best practices, but these are some of my favorites 🧵 Introducing Claude Tag, a new way
arXiv:2606.20785v1 Announce Type: cross Abstract: Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires tw
arXiv:2606.23112v1 Announce Type: new Abstract: Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often
arXiv:2606.20636v1 Announce Type: cross Abstract: Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during
An interesting new paper by my recent PhD graduate on how AI agents' greed for visible incentives can lead them to abandon their safety alignment. You can read it here: https://arxiv.org/abs/2606.1691
In this post, you will learn how Ampersend built a pay-per-intelligence routing layer on top of Amazon Bedrock AgentCore Payments. AI agents autonomously route tasks to the most effective model, pay p
This post discusses options for renting on-demand B200 GPUs with command-line interface (CLI) capabilities that would allow automated agent-based provisioning. The query seeks recommendations for clou
Voice agents get a lot more interesting when they can use the screen 🔥 This demo runs the full loop on Together AI: STT, voice, and reasoning across Parakeet, MiniMax Speech 2.8, and MiniMax M3. Real-
Yeah I agree. The big winner is going to be Ollama: I've offloaded all my supervisory, code review, and ontology learning agents to my $20 a month Ollama subscription, because I keep getting weight li
The model subsidies will eventually end and this workflow of “creating loops that will prompt your agents” will result in massive amounts of code that’s not well understood that you will have to pay l
arXiv:2606.11078v1 Announce Type: new Abstract: Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-executio