# MetaReflection: Learning Instructions for Language Agents using Past Reflections

arXiv: https://arxiv.org/abs/2405.13009 · HTML: https://mlsanity.com/paper/2405.13009/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 13 May 2024.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement](https://mlsanity.com/paper/2305.14497/) (2023)
- [Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models](https://mlsanity.com/paper/2310.13127/) (2023)
- [Semantic HELM: A Human-Readable Memory for Reinforcement Learning](https://mlsanity.com/paper/2306.09312/) (2023)
- [Building Your Own Product Copilot: Challenges, Opportunities, and Needs](https://mlsanity.com/paper/2312.14231/) (2023)
- [The act of remembering: a study in partially observable reinforcement learning](https://mlsanity.com/paper/2010.01753/) (2020)
- [TSTR: Target Similarity Tuning Meets the Real World](https://mlsanity.com/paper/2310.17228/) (2023)

## Built on by (most cited first, 19 of 19)

- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation](https://mlsanity.com/paper/2506.04614/) (2025)
- [Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking](https://mlsanity.com/paper/2505.20023/) (2025)
- [SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection](https://mlsanity.com/paper/2509.20562/) (2025)
- [Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack](https://mlsanity.com/paper/2410.06491/) (2024)
- [TableTalk: Scaffolding Spreadsheet Development with a Language Agent](https://mlsanity.com/paper/2502.09787/) (2025)
- [STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack](https://mlsanity.com/paper/2410.10584/) (2024)
- [From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning](https://mlsanity.com/paper/2604.19516/) (2026)
- [Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents](https://mlsanity.com/paper/2605.25971/) (2026)
- [Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge](https://mlsanity.com/paper/2511.20297/) (2025)
- [Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents](https://mlsanity.com/paper/2604.00830/) (2026)
- [FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards](https://mlsanity.com/paper/2606.06960/) (2026)
- [Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization](https://mlsanity.com/paper/2512.13598/) (2025)
- [STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery](https://mlsanity.com/paper/2605.17790/) (2026)
- [From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps](https://mlsanity.com/paper/2607.23942/) (2026)
- [Do Self-Evolving Skills Generalize to Held-Out Tasks?](https://mlsanity.com/paper/2609.39148/) (2026)
- [Context-Masked Meta-Prompting for Privacy-Preserving LLM Adaptation in Finance](https://mlsanity.com/paper/2407.18920/) (2024)
- [Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis](https://mlsanity.com/paper/2608.21310/) (2026)
- [Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences](https://mlsanity.com/paper/2609.27175/) (2026)

## Abstract (arXiv)

The popularity of Large Language Models (LLMs) have unleashed a new age ofLanguage Agents for solving a diverse range of tasks. While contemporary frontier LLMs are capable enough to power reasonably good Language agents, the closed-API model makes it hard to improve in cases they perform sub-optimally. To address this, recent works have explored ways to improve their performance using techniques like self-reflection and prompt optimization. Unfortunately, techniques like self-reflection can be used only in an online setup, while contemporary prompt optimization techniques are designed and tested to work on simple tasks. To this end, we introduce MetaReflection, a novel offline reinforcement learning technique that enhances the performance of Language Agents by augmenting a semantic memory based on experiential learnings from past trials. We demonstrate the efficacy of MetaReflection by evaluating across multiple domains, including complex logical reasoning, biomedical semantic similarity, open world question answering, and vulnerability threat detection, in Infrastructure-as-Code, spanning different agent designs. MetaReflection boosts Language agents' performance by 4% to 16.82% over the raw GPT-4 baseline and performs on par with existing state-of-the-art prompt optimization techniques while requiring fewer LLM calls.