paper-with-me

Papers

Efficient Exploration for LLMs

2024-02-01 · Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, Benjamin Van Roy

We present evidence of substantial benefit from efficient exploration in gathering human feedback to improve large language models. In our experiments, an agent sequentially generates queries while fitting a reward model to the feedback received. Our best-performing agent generates queries using double Thompson sampling, with uncertainty represented by an epistemic neural network. Our results demonstrate that efficient exploration enables high levels of performance with far fewer queries. Further, both uncertainty estimation and the choice of exploration scheme play critical roles.

📄 PDF Abstract BibTeX arXiv:2402.00396

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient ExplorationThompson Sampling

Similar Papers 제목 키워드 기반

LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps

2025-05-15 · Shanhui Zhao, Hao Wen, Wenjie Du, Cheng Liang 외

Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. Howe…

Action Generation

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

2025-08-11 · Jia Deng, Jie Chen, Zhipeng Chen, Daixuan Cheng 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditional RL approaches, RLVR leverages rule-bas…

Reinforcement Learning

Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Tasks

2025-05-15 · Ziyuan Zhang, Darcy Wang, Ningyuan Chen, Rodrigo Mansur 외

Large language models (LLMs) are increasingly used to simulate or automate human behavior in complex sequential decision-making tasks. A natural question is then whether LLMs exhibit similar decision-making behavior to h…

Decision MakingDecision Making Under UncertaintySequential Decision Making

EVOLvE: Evaluating and Optimizing LLMs For Exploration

2024-10-08 · Allen Nie, Yi Su, Bo Chang, Jonathan N. Lee 외

Despite their success in many domains, large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. This is crucial as many real-world applications, ranging from per…

Decision Making Under UncertaintyMulti-Armed Bandits

EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration

2026-04-08 · Jianfei Wu, Zhichun Wang, Zhensheng Wang, Zhiyu He arxiv

While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial environments remains under-investigated. Existing Geo-Spatial Questi…

Question Answering