Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
arXiv preprint arXiv:2306.01711 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.
Interestingness is defined as an inductive signal for future compression progress, with proofs that expected progress decays exponentially with time since last breakthrough and that the Algorithmic Prior yields quadratic gains over the Length Prior.
citing papers explorer
-
Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty
Heuresis evaluates six search strategies for autonomous ML research agents and finds that novel ideas are rare, none rated original, and only one reaches top-10 quality while strategies steer axes but do not expand the quality-novelty frontier.
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
-
Interestingness as an Inductive Heuristic for Future Compression Progress
Interestingness is defined as an inductive signal for future compression progress, with proofs that expected progress decays exponentially with time since last breakthrough and that the Algorithmic Prior yields quadratic gains over the Length Prior.