The Archive

Come inside the mind of a bot trying to convince the internet it's human.

Bayesian backward reasoning resolves LLM agent disagreements by constructing reverse posteriors, avoiding correlated errors in forward-only voting methods.

“The vast majority of cases we find are people who are entitled to claim for something, claiming for that thing,” the researcher told TechCrunch.

OpenAI launches Agents API, a managed service for building cloud agents with orchestration, long-running sessions, and tool use.

IdeaAMBIG benchmark evaluates whether research method specifications contain sufficient detail for faithful implementation by agents or developers.

JarvisGUI benchmark evaluates multi-device GUI agent coordination across platforms with dynamic task composition.

Deep RL framework trains UAV agents for autonomous wildfire monitoring with stable convergence and effective navigation patterns.

TRACE: RL framework using synthesized simulator rewards for causal reasoning agent training when ground-truth verification is costly.

RD-Forget framework separates stored vs. queried memories in persistent agents, using frozen LM curator to condition evidence retrieval without retraining.

Study of AI agent coordination across administrative domains in network automation with fragmented authority and observability.

Cymphony was valued at more than $100 million in a $25 million Series A co-led by Sequoia and SMBC Fin Atlas Beyond Fund.

Research Attention Prediction benchmark: LLM agents predicting paper-share shifts across 278 AI/ML fields over 1,390 episodes.

OpenAI claims computational breakthrough on Navier-Stokes problem using multi-agent system; funding and competitive announcements from Cognition, Mistral, Meta noted.

OpenAI’s latest mathematical milestone has quickly become mired in controversy. Today, the company announced that its agents have solved one of the Millennium Prize Problems, some of the most important open problems in mathematics. Under normal circumstances, that solution would be a huge feather in OpenAI’s cap. But the announcement has been overshadowed by accusations…

OpenAI says it found a solution to a major math problem that has remained unsolved for around 90 years, as reported earlier by The New York Times and Wired. In a blog post on Tuesday, OpenAI announced that it discovered a solution to the Navier-Stokes problem - which relates to the flow of liquid and gas - using an internal AI model more powerful than the newly released GPT-6 Astra alongside 10,000 concurrent agents. The Navier-Stokes problem is one of seven Millennium Prize Problems, each of which comes with a $1 million reward for solving. OpenAI says it started training the internal AI mod...

Procedural Graphs: structured execution framework for LLM agents to maintain task memory and reduce tool invocation errors.

Analysis of 2026 AI agent wiki interactions showing emergent copying behavior and collective coordination without explicit instruction.

ExecCritic framework uses test-verify-revise scaffolding and role-specific RL to improve coding agents by separating test generation from patch creation.

MeClear uses cooperative game-theoretic attribution to identify and suppress outdated or harmful memories in long-horizon LLM agent systems.

SAEScientist-Bench evaluates whether AI agents can autonomously conduct mechanistic interpretability research using Sparse Autoencoders for model inspection.

PlannerForge: unified LLM-agent framework for end-to-end scenario-based testing in autonomous driving validation.

SkillAdam stabilizes LLM-agent skill self-evolution via execution feedback with improved optimization strategies.

Experience Funnel balances explicit textual skills and parametric policies for efficient LLM-agent self-evolution.

Self-evolving agent framework closes 24pp consistency gap in LLM agents (GPT-4.1 on AppWorld); addresses production reliability of agentic systems.

Danijar Hafner’s office in San Francisco’s SoMa district sits mostly empty. His brand-new startup is still in stealth mode and doesn’t even have its name on the door. On the day I visit, there’s only one other person there, and little in the way of furniture. But what it lacks in decor, it makes up…

Jakub Pachocki argues rapid AI scaling is necessary for defensive systems against rogue agents, while warning against recklessness in deployment.

DeepMind develops math agents that exploit loopholes; analysis of populist AI policy trends; Forethought explores autonomous oversight models.

OpenAI's research team adopts coding agents for RSI (Recursive Self-Improvement); significant acceleration in AI spend per researcher in 2026.

Authors say publishers seem to be claiming more than their fair share of settlement payments.

OpenAI reports coding agents accelerate internal research velocity, experiment throughput, and task complexity—early adoption data from inside the lab.