Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
arXiv:2610.10590v1 Announce Type: new
Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetting: the acting model selects previously observed tool results, replaces each with a short note at i...
Verification and Self-Improvement in Agentic AI: Foundations and Limits
arXiv:2610.10611v1 Announce Type: new
Abstract: Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score does not distinguish these mechanisms. We compare these changes through bounded verification with h...
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
arXiv:2610.10629v1 Announce Type: new
Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is reviewable only if it ...
Roundtables: A Conversation With the Creator of AI-Designed Viruses
Friday, October 16, 2026 Can AI design new life forms? In 2025, Stanford University PhD student Samuel King came up with a preliminary answer when he used a generative AI model to propose genetic blueprints for microscopic viruses. It isn’t yet an example of AI-generated life, but that could be next...
Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended. Developers are combining frontier AI models with NVIDIA Omniverse libraries to help carry out that work — building applications for explori...
Popular AI leaderboard Arena nearly doubles valuation to $3.1B valuation in 10 months
The company behind the popular LMArena leaderboard has raised $200 million led by Lightspeed and Khosla, and is now measuring AI models on alignment issues such as lying.
Google brings agentic AI to Gemini, starting with businesses
Google is turning Gemini into an AI agent that can plan, execute tasks, and work across business apps and systems. The agent can delegate work to subagents, use multiple AI models, and even gets its own workplace identity, complete with an email address.
Anthropic changes usage policy to ban model abuse and election interference
Anthropic's updated usage policy explicitly prohibits users from repeatedly abusing Claude in extreme cases, though ordinary frustration and criticism are still allowed. The new rules also address election interference, deceptive campaigns, weapons software, and surveillance.
Most discussions about AI SEO are still focused on content.How do I get cited by ChatGPT?How do I optimize for Perplexity?What format does an LLM prefer?I think that may only be the first layer.The deeper shift is structural.Today’s websites are largely organized around pages.But an AI agent is tryi...
JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents
JetBrains released Mellum2.1, an Apache 2.0, 12B mixture-of-experts thinking model with 2.5B active parameters. RL in real repositories lifted its SWE-bench Verified score from 2.0 to 47.0.
The post JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents appeared first on MarkTechPost.
Natura’s $99 smart ring puts AI agents on your finger
Natura’s $99 Interface smart ring lets you summon AI agents with the press of a finger to complete tasks, capture thoughts, and control devices — while doubling as a health tracker.
Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost
Goodfire just launched what it says is a cheaper way to keep AI agents in check: instead of paying a second AI to read everything an agent does, its monitors peek inside the model while it works and only call in backup when something looks fishy.
Bridging Algorithmic Design and Regulatory Standards in Enterprise AI
Your models can be both cutting-edge and compliant if you stop treating governance as the final hurdle and start building it into every stage of the ML pipeline.
Docker Agent is an open-source, Apache 2.0-licensed CLI plugin built by Docker Engineering, installed and run as docker agent. Its own tagline states the goal plainly: run AI agents like containers.
AI Agents Beat PyTorch: Writing Faster CUDA Kernels
AI agents can now write CUDA kernels that outperform PyTorch—but proving those speedups are real is the harder problem. I put them to the test on an NVIDIA DGX Spark and found that benchmark design matters just as much as the code.
The post AI Agents Beat PyTorch: Writing Faster CUDA Kernels appeare...
Cal AI’s 19-year-old founder just raised $10M for his new AI startup
Zach Yadegari, the teen co-founder of popular Cal AI calorie tracking app, has launched a new personal AI agent startup that competes with Instinct, Muse and Bee.
China’s Manus raises over $500M in first funding round since split with Meta
Boyu Capital and IDG Capital led the funding round, and existing shareholders Tencent, HSG (formerly known as Sequoia China), ZhenFund and others also participated.
Your Model's MSE Is Lying to You III: Time Series Diffusion
A diffusion head for probabilistic time series forecasting: why a forecast can get the mean and the variance right and still describe a future that never happens, and how to fix it.
The post Your Model's MSE Is Lying to You III: Time Series Diffusion appeared first on Towards Data Science.
AI Engineers, Applied Scientists, Forward Deployed Engineers: Let's Unpack.
An exploration of the new data science roles emerging after the Large Language Model explosion.
The post AI Engineers, Applied Scientists, Forward Deployed Engineers: Let's Unpack. appeared first on Towards Data Science.
AI breakthroughs in robotics won’t change your life any time soon
The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates and supports content about how technology and science are changing the way we live. A robot shaped like a human—white with a black head and torso—has been popping up on video feeds....
Architect Launches Liquid Inference, a Real-Time Auction for LLM Inference
Architect Financial Technologies has launched Liquid Inference, an LLM router that runs a live auction for every request. Liquid Inference is an LLM inference marketplace from Architect where providers bid to serve each prompt. The buyer pays the lowest offer that meets its rules. For developers, it...