paper-with-me

Papers

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting

2024-10-25 · Mohamed Salim Aissi, Clement Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of fine-tuning them with RL in a specific environment. In this paper, we propose a novel framework to analyze the sensitivity of LLMs to prompt formulations following RL training in a textual environment. Our findings reveal that the performance of LLMs degrades when faced with prompt formulations different from those used during the RL training phase. Besides, we analyze the source of this sensitivity by examining the model's internal representations and salient tokens. Finally, we propose to use a contrastive loss to mitigate this sensitivity and improve the robustness and generalization capabilities of LLMs.

📄 PDF Abstract BibTeX arXiv:2410.19920

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingReinforcement Learning (RL)SensitivitySequential Decision Making

Similar Papers 제목 키워드 기반

VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making

2025-05-06 · Jake Grigsby, Yuke Zhu, Michael Ryoo, Juan Carlos Niebles

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs…

Decision MakingGeneral KnowledgeOpen-Ended Question AnsweringQ-Learning+3

ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning

2025-12-21 · Weijie Zhou, Xuangtang Xiong, Ye Tian, Lijun Yue 외 arxiv

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cl…

Reinforcement Learning

Aligning to Social Norms and Values in Interactive Narratives

2022-05-04 · NAACL 2022 7 · Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi 외

We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games -- environments wherein an agent perceives and interacts with a world through natu…

text-based games

STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models

2024-06-09 · Shreyas Basavatia, Keerthiram Murugesan, Shivam Ratnakar

Interactive fiction games have emerged as an important application to improve the generalization capabilities of language-based reinforcement learning (RL) agents. Existing environments for interactive fiction games are …

Reinforcement Learning (RL)text-based games

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

2025-09-17 · Weiting Tan, Xinghua Qu, Ming Tu, Meng Ge 외 arxiv

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, pa…

Reinforcement LearningMathematical Reasoning