PARL: Prompt-based Agents for Reinforcement Learning

• URL: http://arxiv.org/abs/2510.21306v1
• Date: Fri, 24 Oct 2025 10:04:23 GMT
• Title: PARL: Prompt-based Agents for Reinforcement Learning
• Authors: Yarik Menchaca Resendiz, Roman Klinger,
• Abstract summary: Large language models (LLMs) have demonstrated high performance on tasks expressed in natural language.<n>We study structured, non-linguistic reasoning - such as interpreting positions in a grid world.<n>We introduce PARL (Prompt-based Agent for Reinforcement Learning), a method that uses LLMs as RL agents through prompting.
• Score: 8.465228064780742
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) have demonstrated high performance on tasks expressed in natural language, particularly in zero- or few-shot settings. These are typically framed as supervised (e.g., classification) or unsupervised (e.g., clustering) problems. However, limited work evaluates LLMs as agents in reinforcement learning (RL) tasks (e.g., playing games), where learning occurs through interaction with an environment and a reward system. While prior work focused on representing tasks that rely on a language representation, we study structured, non-linguistic reasoning - such as interpreting positions in a grid world. We therefore introduce PARL (Prompt-based Agent for Reinforcement Learning), a method that uses LLMs as RL agents through prompting, without any fine-tuning. PARL encodes actions, states, and rewards in the prompt, enabling the model to learn through trial-and-error interaction. We evaluate PARL on three standard RL tasks that do not entirely rely on natural language. We show that it can match or outperform traditional RL agents in simple environments by leveraging pretrained knowledge. However, we identify performance limitations in tasks that require complex mathematical operations or decoding states and actions.

Related papers

• Language Agents Meet Causality -- Bridging LLMs and Causal World Models [50.79984529172807]
  We propose a framework that integrates causal representation learning with large language models. This framework learns a causal world model, with causal variables linked to natural language expressions. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities.
  arXiv  Detail & Related papers  (2024-10-25T18:36:37Z)
• Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards [49.7719149179179]
  This paper investigates the feasibility of using PPO for reinforcement learning (RL) from explicitly programmed reward signals. We focus on tasks expressed through formal languages, such as programming, where explicit reward functions can be programmed to automatically assess quality of generated outputs. Our results show that pure RL-based training for the two formal language tasks is challenging, with success being limited even for the simple arithmetic task.
  arXiv  Detail & Related papers  (2024-10-22T15:59:58Z)
• Words as Beacons: Guiding RL Agents with High-Level Language Prompts [6.7236795813629]
  Large Language Models (LLMs) as "teachers" guide the agent's learning process by decomposing complex tasks into subgoals. LLMs can provide subgoals to accomplish the task defined for the environment in a similar fashion to how a human would do. It is possible to query the LLM only during the training phase, enabling agents to operate within the environment without any LLM intervention.
  arXiv  Detail & Related papers  (2024-10-11T08:54:45Z)
• From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models [7.704773649029078]
  Vision-language models (VLMs) have tremendous potential for grounding language.<n>This paper introduces a novel decomposition of the problem of building language-conditioned agents (LCAs)<n>We also explore several enhancements to the speed and quality of VLM-based LCAs.
  arXiv  Detail & Related papers  (2024-09-24T12:24:07Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• Large Language Models as Generalizable Policies for Embodied Tasks [50.870491905776305]
  We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment.
  arXiv  Detail & Related papers  (2023-10-26T18:32:05Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)
• Language Models can Solve Computer Tasks [13.914130729517584]
  We show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++.
  arXiv  Detail & Related papers  (2023-03-30T16:01:52Z)
• Collaborating with language models for embodied reasoning [30.82976922056617]
  Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. We present a set of tasks that require reasoning, test this system's ability to generalize zero-shot and investigate failure cases.
  arXiv  Detail & Related papers  (2023-02-01T21:26:32Z)
• Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling [101.59430768507997]
  Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of the world. We propose using few-shot large language models (LLMs) to hypothesize an Abstract World Model (AWM) Our method of hypothesizing an AWM with LLMs and then verifying the AWM based on agent experience not only increases sample efficiency over contemporary methods by an order of magnitude.
  arXiv  Detail & Related papers  (2023-01-28T02:04:07Z)
• Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents [111.33545170562337]
  We investigate the possibility of grounding high-level tasks, expressed in natural language, to a chosen set of actionable steps. We find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into low-level plans. We propose a procedure that conditions on existing demonstrations and semantically translates the plans to admissible actions.
  arXiv  Detail & Related papers  (2022-01-18T18:59:45Z)

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.