Meta-Prompt Optimization for LLM-Based Sequential Decision Making

arXiv:2502.00728 · cs.LG · Submitted 2025-02-02 · Read on arXiv

cs.LG

Submitted: 2025-02-02

Updated: 2026-08-28

Comments: EMNLP 2026 (main)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 19× in this paper · explained in 2 episodes
• Regret — 12× in this paper · explained in 3 episodes
• Embeddings — 11× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Ablation study — 7× in this paper · explained in 1 episode
• In-Context Learning — 7× in this paper · explained in 4 episodes
• Mean Squared Error — 7× in this paper
• Traveling Salesman Problem — 6× in this paper
• Bayesian Optimization — 5× in this paper · explained in 3 episodes
• Non-stationarity — 5× in this paper · explained in 2 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Core — 3× in this paper · explained in 2 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• LLM-Based Multi-Armed Bandits — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• OPRO in the Linear Regression — 1× in this paper
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• Task Facet Learning: A Structured Approach to Prompt Optimization
• A Survey on Data Selection for Language Models
• PRewrite: Prompt Rewriting with Reinforcement Learning
• Can large language models explore in-context?
• Efficient Sequential Decision Making with Large Language Models
• InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
• Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
• In-context Exploration-Exploitation for Reinforcement Learning
• Prompt Optimization with Human Feedback
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• Ambiguity-Aware In-Context Learning with Large Language Models
• AgentBench: Evaluating LLMs as Agents
• PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
• Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
• SmartPlay: A Benchmark for LLMs as Intelligent Agents
• In-context Example Selection with Influences
• Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
• The Rise and Potential of Large Language Model Based Agents: A Survey
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
• Hyperband-based Bayesian Optimization for Black-box Prompt Selection

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks