Skip to main content

Topic: #ai-agents

A collection of 14 posts about ai-agents.

NTU Part II, pages 46–50. Seven worked examples connect SEAL self-edit rewards, two timescales of learning, learned optimizers and MAML. Follow the inner and outer updates and check each reported result against its evaluation unit.

19 min read
#self-improvement#ai-agents#prompt-optimization

NTU Part II, pages 36–40. Follow an edit across generations, compare three parent-selection rules in Hyperagents, and calculate how Learning to Self-Evolve rewards an editor. Seven worked examples separate task performance from editing skill.

19 min read
#self-improvement#ai-agents#prompt-optimization

A Science study asks models to choose questions and tests in sequence. Its reported 83.2% accuracy raises specific questions for clinical validation.

7 min read
#frontier-one#clinical-ai#diagnostic-reasoning
🇰🇷 ko

LEASH uses uncertainty in hidden states to escalate selected computer-use tasks. The preprint compares cost and success on OSWorld and identifies gaps in validation.

7 min read
#frontier-candidate#ai-agents#uncertainty
🇰🇷 ko

Google Research combined lab-state tracking, simulation and execution logs to identify liquid-handling errors and correct experiments in an early demonstration.

7 min read
#frontier-candidate#lab-automation#ai-agents
🇰🇷 ko

The editorial workflow covers checking sources, equations and figures, parallel review, version control, approval and verification after publication. The article identifies the steps already tested and the remaining cloud and Blogger integration work.

14 min read
#ai-agents#technical-writing#publishing-workflow

Read OpenAI’s research automation data through its original diagrams and equations. The analysis covers agent roles, runtime, productivity, limits to parallel work, human intervention, and the denominator behind success rates.

12 min read
#frontier-one#ai-agents#research-automation
🇰🇷 ko