# Retrospex: Language Agent Meets Offline Reinforcement Learning Critic

arXiv: https://arxiv.org/abs/2505.11807 · HTML: https://mlsanity.com/paper/2505.11807/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 17 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)
- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning](https://mlsanity.com/paper/2104.07857/) (2021)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023)
- [Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents](https://mlsanity.com/paper/2305.02412/) (2023)
- [Offline Actor-Critic Reinforcement Learning Scales to Large Models](https://mlsanity.com/paper/2402.05546/) (2024)
- [ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy](https://mlsanity.com/paper/2403.14589/) (2024)
- [Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors](https://mlsanity.com/paper/2307.11922/) (2023)

## Built on by (most cited first, 12 of 12)

- [Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation](https://mlsanity.com/paper/2506.04614/) (2025)
- [Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization](https://mlsanity.com/paper/2602.23008/) (2026)
- [Self-evolving LLM agents with in-distribution Optimization](https://mlsanity.com/paper/2606.07367/) (2026)
- [RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy](https://mlsanity.com/paper/2603.17831/) (2026)
- [Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning](https://mlsanity.com/paper/2505.17607/) (2025)
- [STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery](https://mlsanity.com/paper/2605.17790/) (2026)
- [Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents](https://mlsanity.com/paper/2606.02204/) (2026)
- [MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments](https://mlsanity.com/paper/2606.19893/) (2026)
- [Agent-G2: Gaussian Guidance for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.23318/) (2026)
- [NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries](https://mlsanity.com/paper/2603.05446/) (2026)
- [LifeMem: Enabling Lifelong Experience Reuse for LLM Agents](https://mlsanity.com/paper/2609.12655/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) possess extensive knowledge and commonsense reasoning capabilities, making them valuable for creating powerful agents. However, existing LLM agent frameworks have not fully utilized past experiences for improvement. This work introduces a new LLM-based agent framework called Retrospex, which addresses this challenge by analyzing past experiences in depth. Unlike previous approaches, Retrospex does not directly integrate experiences into the LLM's context. Instead, it combines the LLM's action likelihood with action values estimated by a Reinforcement Learning (RL) Critic, which is trained on past experiences through an offline ''retrospection'' process. Additionally, Retrospex employs a dynamic action rescoring mechanism that increases the importance of experience-based values for tasks that require more interaction with the environment. We evaluate Retrospex in ScienceWorld, ALFWorld and Webshop environments, demonstrating its advantages over strong, contemporary baselines.