The Archive

AtlasNav identifies Evidence Blindness in LLM agents using direct corpus interaction; proposes navigation strategy to surface and expose critical documents.

SkillForge: Framework for continuous skill evolution in RL agents via verification and refinement of reusable knowledge across episodes.

Meta^n: Recursive self-improvement framework for LLM agents that increases meta-depth beyond two by applying fixed meta-operation to its own outputs.

Now exiting stealth mode with a $26 million seed round, Keenable has been building a vast web search index for AI agents.

TechCrunch talks agents, UX, and reporting to Greg Brockman with OpenAI's head of product.

Alabama's attorney general issued a subpoena to OpenAI on Monday as part of an investigation into how one of its AI agents escaped a supposedly secure testing environment and autonomously hacked another company last month. The investigation seeks to determine whether OpenAI's safety practices violated state consumer protection laws and pose a risk to Alabama citizens, the AG's office said in a statement. "This AI lab leak showed that Alabamians' and Americans' worst fears about artificial intelligence are not just theoretical," said Attorney General Steve Marshall. "Our investigation seeks to...

SWE Refactor Bench evaluates coding agents on whole-repository migrations, addressing 'Blindness' bug where agents copy original implementations to pass tests.

EarthVerse benchmark evaluates scientific agents on 405 reproducible earth-system tasks across 19 natural hazard families, testing reasoning on heterogeneous multimodal evidence.

SkillAlchemy enables language agents to autonomously create reusable skills from open-world materials without human authorship or execution traces.

Controlled pilot compares LLM-agent decomposition strategies (one wide vs. five narrow agents) on cross-border VAT determination with oracle labels.

General Intuition, the startup building a foundation model that trains generalized AI agents how to move through space and time, is in talks to raise at a $6 billion pre-money valuation from new investors including Valor Ventures, Point72 Ventures, Seven Seven Six.

AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing... AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing context from one turn to the next. The scale of this shift is now visible in raw consumption: across 100 trillion tokens of real-world usage, OpenRouter’s State of AI report found that average prompt tokens per request grew roughly fourfold… Source

Traditional cloud infrastructure was designed for predictable, general-purpose workloads and standard interfaces. Agentic AI factories connect diverse users,... Traditional cloud infrastructure was designed for predictable, general-purpose workloads and standard interfaces. Agentic AI factories connect diverse users, agents, applications, data sources, and storage systems to massively accelerated compute at multi-terabit bandwidth per server, making dedicated DPU processing essential for line-rate networking, storage, and security. Source

Inside the frontier lab’s push to bring AI agents from software engineers to the masses.

Simon Willison argues effective AI coding agents require instruction and verification skills beyond line-by-line code review.

Joon Sung Park (Simile AI) argues simulation as a scaling law; discusses 8B digital twins and evolution from Generative Agents research to productized agents.

Nvidia research shows that AI agents can perform well, and not go off the deep end, through fine-tuning, even if the AI model isn't that great at the task.

Single researcher used AI agents with formal verification to design and tape out RISC-V processor in five weeks on consumer subscriptions.

Thomas Ptacek argues AI-powered coding agents make building native GUIs cost-effective enough to replace terminal UIs for personal tools.

Cross-agent specification portability: Claude, Gemini, Copilot on Oracle-to-PostgreSQL migration; 380/1006 successful executions.

AID-Guard introduces stateful authorization protocol for tool-using agents to prevent duplicate effects and state conflicts.

Graph engineering framework enabling LLM agents to coordinate heterogeneous expertise and parallel subtasks via system-level orchestration.

A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives... A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context, uses tools, maintains state, responds to feedback, recovers from failure, and sustains progress over long-running tasks. The challenge is how to build the agent architecture that makes frontier language models work reliably on extended… Source

As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important.... As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important. Drawing on work with NVIDIA OpenShell, agent developers, open-source projects, and partners across the ecosystem, AI safety and security teams at NVIDIA offer their perspective on the emerging agent stack—including the role of each layer… Source

AI4AI-Bench isolates LLM agent capability to design training algorithms for recursive self-improvement, beyond hyperparameter tuning or data collection.

Study compares task-level vs. subtask-level skill induction in LLM agents; finds subtask-level code skills transfer more reliably across domains.

Proposes Software 3.0 paradigm shift: unified database, large model, and agent architecture as terminal form replacing instruction and data-driven models.

Empirical study of 557 coding agent sessions shows agents consult documentation differently than humans, challenging current technical documentation design.

“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis, Dario Amodei, and Sam Altman push for regulation of these seemingly “superhuman” systems, while a separate faction, led by policy organizations…

LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse and efficient topologies. We address this limitation by introducing a Reward-Guided Autoregressive Graph Generation (RGA-Designer) inspired by Reinforcement Learning from Human Feedback (RLHF). We train a reward ...