Learning from Mistakes via Cooperative Study Assistant for Large Language Models

Challenge:	Large language models (LLMs) have demonstrated their potential to refine their generation based on their own feedback, but the feedback from LLM itself is often inaccurate, thereby limiting its benefits.
Approach:	They propose a framework with an auxiliary agent to assist the main LLM in learning from mistakes through interactive cooperation.
Outcome:	The proposed framework can significantly boost large language models by an accuracy margin of up to 6.6 on BBH and 12.6 on BBQ.

Similar Papers

Overview

Challenge

Approach

Outcome

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

Responsible & Trustworthy NLP

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)

Copied to clipboard

Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, Fei Huang

Language Models

Challenge:	Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems.
Approach:	They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer.
Outcome:	The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning.

Harnessing Large Language Models as Post-hoc Correctors (2024.findings-acl)

Copied to clipboard

Zhiqiang Zhong, Kuangyu Zhou, Davide Mottin

Language Models

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated their effectiveness in a wide range of tasks, including machine translation and commonsense reasoning.
Approach:	They propose a training-free framework that can work as a post-hoc corrector to propose corrections for ML models.
Outcome:	The proposed framework improves the performance of a number of models by up to 39% on text analysis and the challenging molecular predictions.

Interactive Learning for LLM Reasoning (2026.findings-acl)

Copied to clipboard

Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin

Reasoning

Challenge:	Existing multi-agent learning approaches foster collaboration among Large Language Models (LLMs) yet they still rely on re-executing the MAS during inference.
Approach:	They propose a co-learning framework that integrates Dynamic Interaction and Perception Calibration to enhance LLMs' independent problem-solving ability.
Outcome:	The proposed framework integrates Dynamic Interaction and Perception Calibration to improve LLMs' independent problem-solving ability.

Teaching Language Models to Self-Improve through Interactive Demonstrations (2024.naacl-long)

Copied to clipboard

Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu

Language Models

Challenge:	Large language models (LLMs) have been shown to improve performance on downstream tasks by prompting them to analyze and revise their outputs.
Approach:	They propose a training algorithm that prompts large language models to analyze and revise their own outputs and uses this feedback to train the small model.
Outcome:	The proposed approach improves LLaMA-7B's performance on math and reasoning tasks by up to 7.13%.

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement (2024.findings-emnlp)

Copied to clipboard

Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan

Challenge:	Using advanced Large Language Models, instructors can improve training of smaller models by analyzing their own model's errors.
Approach:	They propose a framework that leverages advanced Large Language Models to enhance training of smaller target models.
Outcome:	The proposed framework outperforms ChatGPT on multiple benchmarks and shows that it improves on both in-domain and out-of-domain benchmarks.

Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)

Copied to clipboard

Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren

Green & Sustainable NLP

Challenge:	Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks.
Approach:	They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately.
Outcome:	The proposed framework outperforms baseline models on three datasets with 14% higher success rate.

Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation (2026.findings-eacl)

Copied to clipboard

Meiqing Jin, Liam Dugan, Chris Callison-Burch

Dialogue Systems & Conversational Agents

Challenge:	Practicing conversations with large language models is a promising alternative to traditional in-person language learning.
Approach:	They propose a new token-level evaluation metric, Token Miss Rate, that measures the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments.
Outcome:	The proposed methods improve comprehensibility for beginner speakers from 39.4% to 83.3%, compared with prompting alone and a token-level evaluation metric, Token Miss Rate (TMR).

Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues (2024.findings-emnlp)

Copied to clipboard

Yuncheng Hua, Lizhen Qu, Reza Haf

Language Models

Challenge:	Existing studies have shown that virtual agents can help humans achieve task and social goals.
Approach:	They propose a tuning-free and label-free method to identify high-quality ICL exemplars for the remediator agent and propose measurable criteria to measure the quality of the negotiation outcomes.
Outcome:	The proposed model is able to improve negotiation outcomes across three negotiation topics.

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

Language Models

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.