Pith. sign in

Title resolution pending

For arm k withN k pulls, reward sumS k, total pullsN tot “ ř j Nj, the UCB score is Uk “ Sk maxpNk,1q `β d log maxpNtot,1q maxpNk,1q , βą0,(30) with β“1 throughout · 2026 · arXiv 0100.0550

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

1 Pith paper citing it
read on arXiv browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

EVE-Agent: Evidence-Verifiable Self-Evolving Agents

cs.AI · 2026-05-21 · unverdicted · novelty 6.0

EVE-Agent adds an evidence verifier to the proposer-solver loop that rewards spans by marginal accuracy gain, producing self-generated but inspectable training examples for search agents.

citing papers explorer

Showing 1 of 1 citing paper.

  • EVE-Agent: Evidence-Verifiable Self-Evolving Agents cs.AI · 2026-05-21 · unverdicted · none · ref 17

    EVE-Agent adds an evidence verifier to the proposer-solver loop that rewards spans by marginal accuracy gain, producing self-generated but inspectable training examples for search agents.