DORA Explorer boosts LLM agent exploration without training by ranking diverse actions using log-probabilities and a tunable parameter, yielding UCB-competitive results on multi-armed bandits and gains on text adventure environments.
Factual Confidence of LLM s: on Reliability and Robustness of Current Estimators
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DORA Explorer: Improving the Exploration Ability of LLMs Without Training
DORA Explorer boosts LLM agent exploration without training by ranking diverse actions using log-probabilities and a tunable parameter, yielding UCB-competitive results on multi-armed bandits and gains on text adventure environments.