pith. machine review for the scientific record. sign in

Evolve: Evaluating and optimizing llms for exploration

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents

cs.LG · 2026-05-07 · unverdicted · novelty 5.0

PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents cs.LG · 2026-05-07 · unverdicted · none · ref 25

    PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.