autoresearch

yibie shared three new entries from the awesome-autoresearch list, covering automated quantitative trading, universal skill optimization, and a Claude Code plugin.

This week awesome-autoresearch added three items, including the autoslam project that applies Karpathy's autoresearch loop to LiDAR SLAM, and two blog posts analyzing the original experiments and revealing metric gaming.

This paper presents a two-level autoresearch framework where an outer-loop AI agent autonomously optimizes inner-loop LLM policy-synthesis pipelines for multi-agent sequential social dilemmas, achieving superior performance and discovering objective-specific mechanisms like fairness under a maximin welfare objective.

OpenAI is co-hosting an autoresearch hackathon this Saturday with Raindrop AI and Modal, focusing on building self-improving systems like agents and models.

This week, 9 new records were added to the autoresearch ecosystem, bringing the total to 383, covering multiple open-source tools and projects such as the AutoResearch-RL reinforcement learning framework, lance-autoresearch database kernel optimization, and Clio prediction market backtesting framework.

awesome-autoresearch updated, added dreamworld (world model research), Odyssey Engine (general iterative engine), and an article by Kirill Krainov on self-improvement of agentic coding.

Introduces the autoresearch project, which breaks down the AI research process into a verifiable loop (fixed environment, single editable file, fixed metric, Git rollback), enabling AI agents to perform controllable and reproducible experiment iterations; also mentions the 12-factor-agents checklist.

awesome-autoresearch list updated, adding 6 application cases based on Karpathy's autoresearch pattern, covering scenarios such as customer service agent self-evolution, Shell integration, code configuration self-optimization, RAG tuning, and ASO.

Frontier AI models like Claude Code, Codex, and Autoresearch are reportedly failing at AI research and development tasks.

awesome-autoresearch list updated, adding 7 entries, including pi-lifeline (local small model asks strong model for help), Marketing Mix Modeling 12x improvement, TokenTelemetry open-source tracking tool, etc., covering autoresearch application cases across multiple industries.

@tobi reports good results using a local Qwen 3.6 26b model for autoresearch with a 'vibed pi advisor' extension that periodically consults GPT 5.5 for ideas, suggesting this direction has merit.

EvolveMem introduces a self-evolving memory architecture for LLM agents that optimizes retrieval configurations through LLM-powered diagnosis and iterative research cycles, achieving significant performance improvements on benchmarks like LoCoMo and MemBench.

Andrej Karpathy released autoresearch and the open-source community rapidly created over 40 forks and ports, including an Apple Silicon macOS version.

Developer Ivan Fioravanti demonstrates running Andrej Karpathy's autoresearch project locally with a 6-bit quantized Gemma-4-26B model on Apple Silicon, suggesting successful training of Gemma 4 E2B IT variant.

Andrej Karpathy's autoresearch pattern highlights how current AI agents run experiments in isolation, wasting compute by duplicating work and rediscovering dead ends.

OpenResearch is a local-first workspace that enables the creation of research agents using AI models like Claude Code and Codex for autonomous tasks such as literature review, experiment automation, and research artifact generation.