paper-with-me

홈 › Papers

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

2024-10-08 · Zaid Khan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

The process of creating training data to teach models is currently driven by humans, who manually analyze model weaknesses and plan how to create data that improves a student model. Approaches using LLMs as annotators reduce human effort, but still require humans to interpret feedback from evaluations and control the LLM to produce data the student needs. Automating this labor-intensive process by creating autonomous data generation agents - or teachers - is desirable, but requires environments that can simulate the feedback-driven, iterative, closed loop of data creation. To enable rapid, scalable testing for such agents and their modules, we introduce DataEnvGym, a testbed of teacher environments for data generation agents. DataEnvGym frames data generation as a sequential decision-making task, involving an agent consisting of a data generation policy (which generates a plan for creating training data) and a data generation engine (which transforms the plan into data), inside an environment that provides student feedback. The agent's goal is to improve student performance. Students are iteratively trained and evaluated on generated data, and their feedback (in the form of errors or weak skills) is reported to the agent after each iteration. DataEnvGym includes multiple teacher environment instantiations across 3 levels of structure in the state representation and action space. More structured environments are based on inferred skills and offer more interpretability and curriculum control. We support 4 domains (math, code, VQA, and tool-use) and test multiple students and teachers. Example agents in our teaching environments can iteratively improve students across tasks and settings. Moreover, we show that environments teach different skill levels and test variants of key modules, pointing to future work in improving data generation agents, engines, and feedback mechanisms.

📄 PDF Abstract BibTeX arXiv:2410.06215

Code (1)

codezakh/dataenvgym 공식 구현

Tasks

MathSequential Decision MakingVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Enhancing the Hierarchical Environment Design via Generative Trajectory Modeling

2023-09-30 · Dexun Li, Pradeep Varakantham

Unsupervised Environment Design (UED) is a paradigm for automatically generating a curriculum of training environments, enabling agents trained in these environments to develop general capabilities, i.e., achieving good …

Trajectory Modeling

Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning

2026-02-10 · Dexun Li, Sidney Tio, Pradeep Varakantham arxiv

Unsupervised Environment Design (UED) has emerged as a promising approach to developing general-purpose agents through automated curriculum generation. Popular UED methods focus on Open-Endedness, where teacher algorithm…

Representation Learning

Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

2025-05-25 · Debdeep Sanyal, Agniva Maiti, Umakanta Maharana, Dhruv Kumar 외

Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teacher training. While Large Language Model…

RAGRetrievalRetrieval-augmented Generation

MASAI: Multi-agent Summative Assessment Improvement for Unsupervised Environment Design

2021-06-13 · ICML Workshop URL 2021 7 · Yiping Wang, Michael Brandon Haworth

Reinforcement Learning agents require a distribution of environments for their policy to be trained on. The method or process of defining these environments directly impacts robustness and generalization of the learned a…

Heuristic Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward Scenarios

2024-05-23 · Emma Clark, Kanghyun Ryu, Negar Mehr

Learning from Demonstration (LfD) can be an efficient way to train systems with analogous agents by enabling ``Student'' agents to learn from the demonstrations of the most experienced ``Teacher'' agent, instead of train…