# Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents

arXiv: https://arxiv.org/abs/2502.10732 · HTML: https://mlsanity.com/paper/2502.10732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 15 Feb 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://mlsanity.com/paper/2406.04151/) (2024)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Concept-based Explainable Artificial Intelligence: A Survey](https://mlsanity.com/paper/2312.12936/) (2023)
- [Gymnasium: A Standard Interface for Reinforcement Learning Environments](https://mlsanity.com/paper/2407.17032/) (2024)
- [A Critical Look At Tokenwise Reward-Guided Text Generation](https://mlsanity.com/paper/2406.07780/) (2024)
- [Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games](https://mlsanity.com/paper/2408.15950/) (2024)
- [Optimizing Vital Sign Monitoring in Resource-Constrained Maternal Care: An RL-Based Restless Bandit Approach](https://mlsanity.com/paper/2410.08377/) (2024)
- [Natural Language Reinforcement Learning](https://mlsanity.com/paper/2411.14251/) (2024)
- [Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation](https://mlsanity.com/paper/2311.18062/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI](https://mlsanity.com/paper/2508.21101/) (2025)

## Abstract (arXiv)

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and adaptability, challenging their deployment alongside human decision-makers. In contrast, Language Agents, powered by large language models (LLMs), provide human-understandable reasoning but may struggle with effective decision making. To bridge this gap, we propose Rule-Bottleneck Reinforcement Learning (RBRL), a novel framework that jointly optimizes decision and explanations. At each step, RBRL generates candidate rules with an LLM, selects among them using an attention-based RL policy, and determines the environment action with an explanation via chain-of-thought reasoning. The RL rule selection is optimized using the environment rewards and an explainability metric judged by the LLM. Evaluations in real-world scenarios highlight RBRL's competitive performance with deep RL and efficiency gains over LLM fine-tuning. A survey further confirms the enhanced quality of its explanations.