Agents, open-endedness, AGI — page 1
- A Comprehensive Evaluation of Tool-Assisted Generation Strategies
url:research.google/blog/few-shot-tool-use-doesnt-really-work-yet· 2024-05-30 · metadata only - A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
arxiv:2311.00344· 2023-11-01 · text available - A social path to human-like artificial intelligence
doi:10.1038/s42256-023-00754-x· 2023-11-01 · text available - AI Finds A Way
arxiv:2608.23875· 2026-08-26 · text available - AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
arxiv:1905.10985· 2019-05-27 · text available - AlphaGo Moment for Model Architecture Discovery
arxiv:2507.18074· 2025-07-24 · text available - Automated Design of Agentic Systems
arxiv:2408.08435· 2024-08-15 · text available - Competition and Attraction Improve Model Fusion
arxiv:2508.16204· 2025-08-22 · text available - Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
arxiv:2505.22954· 2025-05-29 · text available - Dr. Zero: Self-Evolving Search Agents without Training Data
arxiv:2601.07055· 2026-01-11 · text available - Dream-RSI: Recursive Self-Improvement through Evolving Worlds
arxiv:2609.14858· 2026-09-14 · text available - Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
arxiv:2410.04444· 2024-10-06 · text available - Harnessing Agentic Evolution
arxiv:2605.13821· 2026-05-13 · text available - Hyperagents
arxiv:2603.19461· 2026-03-19 · text available - Language Agents as Optimizable Graphs
arxiv:2402.16823· 2024-02-26 · text available - Learning Formal Mathematics From Intrinsic Motivation
arxiv:2407.00695· 2024-06-30 · text available - Learning to Continually Learn via Meta-learning Agentic Memory Designs
arxiv:2602.07755· 2026-02-08 · text available - Levels of AGI for Operationalizing Progress on the Path to AGI
arxiv:2311.02462· 2023-11-04 · text available - LLM Powered Autonomous Agents (Lilian Weng)
url:lilianweng.github.io/posts/2023-06-23-agent· 2023-06-23 · metadata only - Mathematical discoveries from program search with large language models
doi:10.1038/s41586-023-06924-6· 2023-12-14 · text available - MemEvolve: Meta-Evolution of Agent Memory Systems
arxiv:2512.18746· 2025-12-21 · text available - MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
arxiv:2601.03192· 2026-01-06 · text available - Meta Context Engineering via Agentic Skill Evolution
arxiv:2601.21557· 2026-01-29 · text available - MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
url:minedojo.org· 2022-06-17 · metadata only