Jagged capabilities in LLMs for scientific idea generation can be leveraged through inference-time ensembles to outperform individual models.
Addressing llm diversity by infusing random concepts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2years
2026 2roles
background 1polarities
background 1representative citing papers
Embodied LLMs achieve higher puzzle-solving success with raw RGB observations than ground-truth symbolic ones, with moderate action-outcome noise boosting rates 2.85-fold by reducing repetitive loops.
citing papers explorer
-
LLM Jaggedness Unlocks Scientific Creativity
Jagged capabilities in LLMs for scientific idea generation can be leveraged through inference-time ensembles to outperform individual models.
-
Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving
Embodied LLMs achieve higher puzzle-solving success with raw RGB observations than ground-truth symbolic ones, with moderate action-outcome noise boosting rates 2.85-fold by reducing repetitive loops.