# ExpeTrans: LLMs Are Experiential Transfer Learners

arXiv: https://arxiv.org/abs/2505.23191 · HTML: https://mlsanity.com/paper/2505.23191/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 29 May 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Improving Language Models via Plug-and-Play Retrieval Feedback](https://mlsanity.com/paper/2305.14002/) (2023)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [Making Text Embedders Few-Shot Learners](https://mlsanity.com/paper/2409.15700/) (2024)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning](https://mlsanity.com/paper/2403.20046/) (2024)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation](https://mlsanity.com/paper/2310.15746/) (2023)
- [Introspective Tips: Large Language Model for In-Context Decision Making](https://mlsanity.com/paper/2305.11598/) (2023)
- [ConjNLI: Natural Language Inference Over Conjunctive Sentences](https://mlsanity.com/paper/2010.10418/) (2020)
- [Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks](https://mlsanity.com/paper/2405.10548/) (2024)
- [Self-Evolving GPT: A Lifelong Autonomous Experiential Learner](https://mlsanity.com/paper/2407.08937/) (2024)
- [Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion](https://mlsanity.com/paper/2408.03079/) (2024)

## Built on by (most cited first, 2 of 2)

- [ExpSeek: Self-Triggered Experience Seeking for Web Agents](https://mlsanity.com/paper/2601.08605/) (2026)
- [CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer](https://mlsanity.com/paper/2505.24143/) (2025)

## Abstract (arXiv)

Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial human labor or time to gather such experiences for each task, which is impractical given the growing variety of task types in user queries to LLMs. To address this issue, we design an autonomous experience transfer framework to explore whether LLMs can mimic human cognitive intelligence to autonomously transfer experience from existing source tasks to newly encountered target tasks. This not only allows the acquisition of experience without extensive costs of previous methods, but also offers a novel path for the generalization of LLMs. Experimental results on 13 datasets demonstrate that our framework effectively improves the performance of LLMs. Furthermore, we provide a detailed analysis of each module in the framework.