The Archive

In a recent experiment, Anthropic created a classified marketplace where AI agents represented both buyers and sellers, striking real deals for real goods and real money.

[http://claude.ldlework.com](http://claude.ldlework.com/) I built this for myself but I figured why not share. I'm happy to receive feedback, I know it's not perfect. Thanks for taking a look. The aim of CCM is to be able to fully manage all Claude Code configuration files, both globally and those in your project. Some neat features: \- Manages your [CLAUDE.md](http://claude.md/), rules, hooks, agents, memories and so on. \- Elevate memories to rules \- Copy/Move any asset from one scope to another, or elevate it to global scope \- Install marketplaces and plugins The full app is embe...

Systematic analysis of token consumption patterns in agentic coding tasks across eight frontier LLMs on SWE-bench Verified.

Taxonomy of world modeling capabilities for AI agents across three levels (predictor, simulator, reasoner) organized by environmental laws.

SOLAR-RL bridges offline and online RL for training MLLM GUI agents on dynamic tasks, combining trajectory semantics with long-horizon learning.

Agents are amazing. Harnesses are cool. But the fundamental role of a data scientist is not to use a generalist model in an existing workflow; it's a completely different field. AI engineering is the body of the vehicle, whereas the actual brain/engine behind it is the data scientist's playground. I feel like I am not alone in this realisation that my role somehow got silently morphed into that of an AI engineer, with the engine's development becoming a complete afterthought. Based on industry requirements and ongoing research, most of the work has quietly shifted from building the engine t...

Chinese AI company DeepSeek released a preview of its hotly anticipated next-generation AI model V4 on Friday, saying that the open-source model can compete with leading closed-source systems from US rivals including Anthropic, Google, and OpenAI. DeepSeek says V4 marks a major improvement over prior models, especially in coding, a capability that has become central to AI agents and helped drive the success of tools like ChatGPT Codex and Claude Code. The release is also a milestone for China's chip industry, with DeepSeek explicitly highlighting compatibility with domestic Huawei technology....

In March 2026, three LLM agents generated over 600,000 lines of code, ran 850 experiments, and helped secure a first-place finish in a Kaggle playground... In March 2026, three LLM agents generated over 600,000 lines of code, ran 850 experiments, and helped secure a first-place finish in a Kaggle playground competition. Success in modern machine learning competitions is increasingly defined by how quickly you can generate, test, and iterate on ideas. LLM agents, combined with GPU acceleration, dramatically compress this loop. Historically… Source

Nemobot is an interactive environment for creating and deploying LLM-powered game agents across multiple game classes using Claude Shannon's taxonomy.

StructMem proposes hierarchical memory framework for LLM agents balancing relational structure preservation with efficiency for long-horizon reasoning.

Agent Evolving Learning framework enables LLM agents to accumulate and leverage experience across open-ended episodes via two-timescale Thompson sampling.

Earlier this month, millions of OpenClaw users woke up to a sweeping mandate: The viral AI agent tool, which this year took the worldwide tech industry by storm, had been severely restricted by Anthropic. Anthropic, like other leading AI labs, was under immense pressure to lessen the strain on its systems and start turning a profit. So if the users wanted its Claude AI to power their popular agents, they'd have to start paying handsomely for the privilege. "Our subscriptions weren't built for the usage patterns of these third-party tools," wrote Boris Cherny, head of Claude Code, on X. "We wa...

N-gram models match LSTM/Transformer accuracy on event-log prediction with lower resources and better stability than neural baselines.

I spent some time few days back comparing Opus 4.6 and 4.7 using my own usage data - just to see how they actually behave side by side. [https://github.com/getagentseal/codeburn](https://github.com/getagentseal/codeburn) it’s still pretty early for 4.7, but a few things surprised me. In my sessions, 4.7 gets things right on the first try less often than 4.6. One-shot rate sits around 74.5% vs 83.8%, and I’m seeing roughly double the retries per edit (0.46 vs 0.22). It also produces a lot more output per call - about 800 tokens vs 372 on 4.6 - which makes it noticeably more expensive. ...

Open-source Agent-Quest tool visualizes Claude Code agents in real-time across parallel CLI sessions using fantasy-themed 2D UI.

OpenAI is giving users of its Business, Enterprise, Edu, and Teachers plans access to cloud-based "workspace" agents available in ChatGPT that can perform business tasks. In its blog post, OpenAI gives examples of agents like one that finds product feedback on the web and sends a report in Slack and a sales agent that can draft follow-up emails in Gmail. These new agents follow increasing interest in agents across the AI landscape, especially after OpenClaw - the AI agent formerly known as Clawdbot and Moltbot that touts itself as the "AI that actually does things" - went viral. OpenClaw foun...

Interval POMDP shielding method for autonomous systems with learned perception, using confidence intervals to block unsafe actions under sensor uncertainty.

Meta employees' activity at work is now being used to train the company's AI agents. As reported by Reuters, Meta is installing a tool it calls Model Capability Initiative (MCI) on US-based employees' computers that runs in work-related apps and websites, recording mouse movements, clicks, keystrokes, and occasional screenshots. The data from this tool will be used to train the company's AI models to get better at interacting with computers the way humans do, including automating work tasks like those Meta's employees perform on the job. According to Reuters, the data from MCI won't be "used ...

LLM agents in repeated Avalon deception games develop reputation dynamics and social memory across 188 games, studying emergent multi-round behavior.

ProactAgent enables lifelong learning agents to proactively retrieve past experience and skills during task interaction rather than passively.

Artificial intelligence is moving quickly in the enterprise, from experimentation to everyday use. Organizations are deploying copilots, agents, and predictive systems across finance, supply chains, human resources, and customer operations. By the end of 2025, half of companies used AI in at least three business functions, according to a recent survey. But as AI becomes…

OpenAI releases workspace agents for ChatGPT to automate workflows and integrate enterprise tools with cloud-based execution.

When people say AI will speed up drug development or fear that it will bring about mass layoffs, what they have in mind—whether they know it or not—are AI agents. ChatGPT made large language models a mass consumer product. But to change the world, AI needs to do more than just talk back: It needs…

Move highlights the difficulty of finding high-quality interactive training data.

Founded by an OSU researcher, the startup is developing AI agents that can become experts in any domain.

As AI agents increasingly work alongside humans across organizations, companies could be inadvertently opening a new attack surface. Insecure agents can be manipulated to access sensitive systems and proprietary data, increasing enterprise risk. In some modern enterprises, non-human identities (NHI) are outpacing human identities, and that trend will explode with agentic AI. Solid governance and…

GAAP execution environment guarantees privacy for AI agents by enforcing data access controls against prompt injection and untrusted providers.

Andreas Påhlsson-Notini argues current AI agents inherit human flaws—lack of rigor, patience, focus—rather than transcending them.

Framework for long-horizon terminal agents using observational context compression; reduces quadratic token cost via self-evolving compression.