A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yizhe Chi, Wenyi Li, Deyao Hong, et al.
AI4AI-Bench benchmarks LLM agents on rewriting training algorithms across 10 repositories, finding best agents close only a fifth of the gap to optimal.
Yaxin Luo, Haobin Jiang, Jialv Zou, et al.
AutoDesign introduces a meta-harness optimization framework for long-horizon agentic design, achieving state-of-the-art paper-to-poster generation with recursive self-improvement.
Gaytri Jena, Kapil Wanaskar, Vinija Jain, et al.
A survey organizing robot learning around the weights-versus-skills axis, analyzing code-as-policy self-improvement and the emerging skill economy.
Taofeng Xue, Chong Peng, Mianqiu Huang, et al.
Evocua introduces a scalable synthetic experience generation framework that evolves computer-use agents through iterative self-improvement, overcoming static data bottlenecks.
Unknown
A reinforcement learning paradigm where a single model learns to propose tasks maximizing its own learning progress and improves reasoning by solving them, enabling continuous self-improvement without human data.
Unknown
Multiagent Finetuning improves LLMs by training specialized generation and critic agents on debate-generated data, enabling iterative self-improvement with diverse reasoning.