Seonglae ChoDGM
For each modification (experiment), we perform benchmark testing for empirical validation and archive the results (knowledge accumulation). This automates the research cycle. Rather than single-goal optimization, it focuses on discovering new ideas and algorithms through exploration-research. Going beyond human-designed fixed structures, AI modifies and validates code by itself for endless self-improvement → achieving cumulative and open-ended development like scientific discovery. Open-ended exploration: Creates diverse 'stepping stones' to diversify search paths and escape local optima.
Results
Key improvements found are tool refinement, multi-patch evaluation, etc.
- SWE-bench success rate 20% → 50%
- Polyglot success rate 14.2% → 30.7%
While it's not exactly a fair comparison since the baseline removed self-improvement and open-ended elements, this is one of the few cases where Evolutionary algorithm has shown efficiency in AI Agent and LLM applications.
HyperAgents
Pushes DGM's limits one step further by including in the editable program not only the task agent but also the meta-agent that improves agents.
