When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?

• URL: http://arxiv.org/abs/2605.30719v1
• Date: Fri, 29 May 2026 01:24:24 GMT
• Title: When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
• Abstract summary: Large language models (LLMs) can serve as effective black-box policy models for reinforcement learning tasks.<n>We introduce Prompted Policy Optimization (PromptPO), an iterative method that prompts an LLM with Python descriptions of the state space, action space, and reward function.<n>PromptPO often matches or exceeds the performance of standard RL baselines while using substantially fewer environment interactions.
• Score: 15.079504478885953
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.e., when can we replace classical RL algorithms with an LLM? We explore this question by introducing Prompted Policy Optimization (PromptPO), an iterative method that prompts an LLM with Python descriptions of the state space, action space, and reward function, then has it generate and refine executable policies based on rollout feedback. Across hard exploration environments, Meta-World robotics tasks, and several real-world control problems, PromptPO often matches or exceeds the performance of standard RL baselines while using substantially fewer environment interactions. To maximize expected return, and without further explicit prompting, the policies PromptPO outputs range from tuned proportional controllers or rule-based plans to policies that run planning algorithms like value iteration. Our results demonstrate that LLM-based policy optimization is sufficient when the LLM can leverage prior knowledge about the environment or optimization strategy. PromptPO underperforms standard RL baselines in MuJoCo domains. This demonstrates possible limitations of LLM-based policy optimization to settings that requiring fine-grained continuous control.

Related papers

• Towards Harnessing the Power of LLMs for ABAC Policy Mining [0.0468771281852187]
  This paper presents an empirical investigation into the capabilities of Large Language Models (LLMs) to perform automated Attribute-based Access Control (ABAC) policy mining.<n>We evaluate the performance of some of the state-of-the-art LLMs, specifically Google Gemini (Flash and Pro) and OpenAI ChatGPT, as potential policy mining engines.
  arXiv  Detail & Related papers  (2025-11-22T15:49:36Z)
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM [14.139788456751706]
  We investigate the usage of Large Language Model (LLM) in collecting high-quality data to warm-start Reinforcement Learning (RL) algorithms.<n>Our algorithm, LORO, can both converge to an optimal policy and have a high sample efficiency.<n>On multiple OpenAI Gym environments, such as CartPole and Pendulum, we empirically demonstrate that LORO outperforms baseline algorithms.
  arXiv  Detail & Related papers  (2025-05-16T05:03:39Z)
• Large Language Model driven Policy Exploration for Recommender Systems [50.70228564385797]
  offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments.<n>Online RL-based RS also face challenges in production deployment due to the risks of exposing users to untrained or unstable policies.<n>Large Language Models (LLMs) offer a promising solution to mimic user objectives and preferences for pre-training policies offline.<n>We propose an Interaction-Augmented Learned Policy (iALP) that utilizes user preferences distilled from an LLM.
  arXiv  Detail & Related papers  (2025-01-23T16:37:44Z)
• Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone [72.17534881026995]
  We develop an offline and online fine-tuning approach called policy-agnostic RL (PA-RL)<n>We show the first result that successfully fine-tunes OpenVLA, a 7B generalist robot policy, autonomously with Cal-QL, an online RL fine-tuning algorithm.
  arXiv  Detail & Related papers  (2024-12-09T17:28:03Z)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• POPO: Pessimistic Offline Policy Optimization [6.122342691982727]
  We study why off-policy RL methods fail to learn in offline setting from the value function view. We propose Pessimistic Offline Policy Optimization (POPO), which learns a pessimistic value function to get a strong policy. We find that POPO performs surprisingly well and scales to tasks with high-dimensional state and action space.
  arXiv  Detail & Related papers  (2020-12-26T06:24:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.