arXiv Machine Learning August 31, 2026 By Mingze Kong, Zhiyong Wang, Yao Shu, Zhongxiang Dai

Meta-Prompt Optimization for LLM-Based Sequential Decision Making

Read the original on arXiv Machine Learning →

The paper introduces EXPO, an algorithm that automatically optimizes the meta-prompt—specifically the task description and meta-instruction—for large language model agents in sequential decision-making tasks such as Bayesian optimization and multi-armed bandits. Building on adversarial bandit techniques to handle non-stationary rewards, the authors extend EXPO to EXPO-ES, which also optimizes exemplars (historical interactions) within the meta-prompt. Experiments demonstrate that these methods significantly improve the performance of LLM-based agents in sequential decision-making scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 13

DORA Explorer: Improving the Exploration Ability of LLMs Without Training

arXiv:2604. 17244v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents for sequential decision-making struggle to produce diverse outputs.

By Priya Gurjar, Md Farhan Ishmam, Kenneth Marino

llms agents reinforcement-learning

Hugging Face Trending Papers

Jul 30

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation.

llms reinforcement-learning benchmarks

arXiv Computation and Language

1d ago

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

arXiv:2607.28077v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...

By Shuang Liang, Haoyang Zhou, Yifan Gong, Guowei Wang, Xiting Wang

llms reinforcement-learning benchmarks

arXiv AI

Aug 5

In-Context Pure Exploration in Continuous Decision Spaces

arXiv:2602. 17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible.

By Alessio Russo, Yin-Ching Lee, Ryan Welch, Aldo Pacchiano

reinforcement-learning

arXiv AI

Jun 10

3SPO: State-Score-Supervised Policy Optimization for LLM Agents

arXiv:2606. 09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks.

By Yu Han, Kailing Li, Yang Jiao, Yulin Dai, Yuqian Fu, Linhai Zhuo, Tianwen Qian

llms agents reinforcement-learning

arXiv AI

Aug 18

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors

arXiv:2608. 16707v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration.

By David Eric Austin, Kaheer Suleman, Jackie Chi Kit Cheung

llms agents reinforcement-learning safety

One email a morning, machine-written

Related stories

DORA Explorer: Improving the Exploration Ability of LLMs Without Training

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

In-Context Pure Exploration in Continuous Decision Spaces

3SPO: State-Score-Supervised Policy Optimization for LLM Agents

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors