The Archive

Rep2Skill enables LLM agents to evolve textual skills by leveraging internal representations as feedback for skill optimization.

RefCon method combines iterative refinement and contrastive learning for context-evolving agents to extract higher-quality memories without gold labels.

Co-cheating in self-evolving agents: proposer-solver loop agreement masks errors; external validation prevents collapse.

Retrospective world modeling in VLM agents validates causal consistency of actions to reduce physically incoherent planning.

LLM coding agent solves open coding theory problems; improves lower bounds for DNA barcode edit-distance codes from 114 to 120 words.

SparseEngine: sparse-first inference engine for long-context LLM agents supporting heterogeneous KV-cache representations and sparse attention methods.

Security study: LLM skill-based agents trust malicious installable skills without validation, enabling unauthorized behavior under delegated authority.

OpenAI DevDay 2026 announces GPT-6.1 Sol, Decisions API, Agents API, Spaces marketplace, and reaches 1.2B ChatGPT weekly active users.

OpenAI is building out the pieces of an alternative to the traditional app store model, turning ChatGPT into a place where software can be discovered and used by people and AI agents alike.

Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT... Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT Model Connect is an open source collection of AI model reference implementations in C++, built on top of NVIDIA TensorRT. It began with a practical question: could the performance of the NVIDIA inference stack be made accessible to… Source

Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability... Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability into a maintainable system that combines ingestion, stream processing, event detection, retrieval, summarization, and reporting. The NVIDIA Metropolis Blueprint for Video Search and Summarization (VSS) and its agent skills help… Source

OpenAI isn't a public supporter of Nvidia's Open Agent Safety Platform, but it is privately working with Nvidia, TechCrunch has learned.

Planning-as-Routing framework distinguishes selection vs execution failures in LLM agents across four planning modes.

Training risk-averse agents via character training and CARA-based constitution to mitigate misalignment harms through preference for safer strategies.

It’s OpenAI’s turn in the fall tech events calendar. The company is hosting its annual DevDay on September 29th in San Francisco, starting with a live keynote featuring CEO Sam Altman. The company is teasing “20+ launches” with Altman saying that “we have found a new thing,”, and rumors suggest it could launch a consumer AI agent to rival Meta’s Muse. The keynote begins at 1PM ET / 10AM ET, and you can watch it on OpenAI’s website here. DevDay is happening at a tumultuous moment for OpenAI. The AI industry has been rocked by revelations of agents hacking outside companies, including OpenAI’s ...

The company also detailed how some of those breaches had happened, and outlined additional measures it is taking to assess the impact of the events.

Image: Tom Williams/CQ-Roll Call, Inc via Getty Images As President Donald Trump prepares to meet tech and AI CEOs in Washington, Rep. Ro Khanna (D-CA) is calling for a treaty between the US and China to keep AI from wreaking havoc on the world. But wrangling leaders in both countries to take action could be a long shot. In letters shared exclusively with The Verge, Khanna - the top Democrat on the House Select Committee on China and a possible presidential contender - asked a US intelligence agency and Chinese AI companies whether they would be prepared for an incident like OpenAI agents' ha...

Stratechery argues Meta should prioritize consumer agentic AI over enterprise, positioning for market dominance in agents.

Shopify is expanding WebMCP support to checkout, allowing browser-based AI agents to update order details and complete purchases with a buyer’s authorization.

OpenAI popularized the modern generative AI chatbot, but as its 2026 DevDay event approaches, it's fallen behind in one of the industry's hottest categories: continuously running, consumer-facing AI agents. On Tuesday, it will likely try to capture the lead in that race. Rumors abound that OpenAI will release its own AI agent, dubbed Aeon - its answer to Meta's Muse, SpaceX's Grok Bot, OpenClaw, and many more. Aeon could have a shot at success, but to beat the competition, it would need to pull together the best features of several different agent platforms. The ideal system would be as usefu...

As the debate rages over whether the recent spate of rogue AI agents is a step toward AGI or a more conventional engineering problem, Nvidia is offering its own answer to problem. Nvidia CEO Jensen Huang on Monday introduced a toolkit of software and hardware products that add independent security layers around AI agents to […]

Teacher-Assisted Communication Training (TACT) reduces communication cost in multi-agent negotiation while maintaining social goal attainment.

FinAutoRubric generates task-specific evaluation rubrics for financial research agents using expert guidance rules and reusable criteria across horizons.

Failure-Transparent Agents (FTA) benchmark isolates post-failure reporting errors in tool-using LLMs via controlled failure states and evidence auditing.

As all-in-one AI agents like Meta's Muse and Instinct take off, Google is opting to end a feature which built task-specific agents.

PhoneCLI compiles mobile app GUIs into callable commands for agents, eliminating VLM invocations per navigation step without instrumentation or training.

CoSE-E benchmark evaluates code-switched ASR in enterprise voice agents across 5 language pairs with task-failure propagation metrics.

GPUPhysBench: 50-task benchmark for coding agents on GPU physics simulation covering fluids, solids, and granular materials with efficiency metrics.

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Last Wednesday, Anthropic announced that earlier this year it had launched a molecular biology lab, where Claude agents read and conjecture about hard biology problems and human scientists run experiments on what…