DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

• URL: http://arxiv.org/abs/2507.23554v1
• Date: Thu, 31 Jul 2025 13:42:14 GMT
• Title: DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer
• Authors: Ruoyu Wang, Junda Wu, Yu Xia, Tong Yu, Ryan A. Rossi, Julian McAuley, Lina Yao,
• Abstract summary: Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks.<n>Existing approaches typically rely on example selection, including in some agentic or multi-step settings.<n>We propose DICE, a theoretically grounded ICL framework for agentic tasks that selects the most relevant demonstrations at each step of reasoning.
• Score: 50.64531021352504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks. However, existing works have shown that the effectiveness of ICL is highly sensitive to the choice of demonstrations, with suboptimal examples often leading to unstable or degraded performance. While prior work has explored example selection, including in some agentic or multi-step settings, existing approaches typically rely on heuristics or task-specific designs and lack a general, theoretically grounded criterion for what constitutes an effective demonstration across reasoning steps. Therefore, it is non-trivial to develop a principled, general-purpose method for selecting demonstrations that consistently benefit agent performance. In this paper, we address this challenge with DICE, Dynamic In-Context Example Selection for LLM Agents, a theoretically grounded ICL framework for agentic tasks that selects the most relevant demonstrations at each step of reasoning. Our approach decomposes demonstration knowledge into transferable and non-transferable components through a causal lens, showing how the latter can introduce spurious dependencies that impair generalization. We further propose a stepwise selection criterion with a formal guarantee of improved agent performance. Importantly, DICE is a general, framework-agnostic solution that can be integrated as a plug-in module into existing agentic frameworks without any additional training cost. Extensive experiments across diverse domains demonstrate our method's effectiveness and generality, highlighting the importance of principled, context-aware demo selection for robust and efficient LLM agents.

Related papers

• Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why [50.191655141020505]
  This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations.<n>We argue that the dichotomy between feature-based and GAN-based methods is increasingly nuanced.
  arXiv  Detail & Related papers  (2025-07-08T11:45:51Z)
• Leveraging In-Context Learning for Language Model Agents [51.2996117207114]
  In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance.<n>We show that set-selection of trajectories of similar tasks as demonstrations significantly improves performance, reliability, robustness, and efficiency of LLM agents.<n>We find that demonstrations obtained from larger models (in the annotation phase) also improve smaller models, and that ICL agents can even rival costlier trained agents.
  arXiv  Detail & Related papers  (2025-06-16T05:37:49Z)
• Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning [45.06983025267863]
  This paper investigates ICL on Large Vision-Language Models (LVLMs) and explores the policies of multi-modal demonstration selection.<n>We propose a new exploration-exploitation reinforcement learning framework, which explores policies to fuse multi-modal information and adaptively select adequate demonstrations as an integrated whole.
  arXiv  Detail & Related papers  (2025-06-11T07:38:12Z)
• Towards more Contextual Agents: An extractor-Generator Optimization Framework [0.0]
  Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications.<n>However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains.<n>To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents.
  arXiv  Detail & Related papers  (2025-02-18T15:07:06Z)
• CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing [70.25689961697523]
  We propose a generalizable algorithm that enhances sequential reasoning by cross-task experience sharing and selection. Our work bridges the gap between existing sequential reasoning paradigms and validates the effectiveness of leveraging cross-task experiences.
  arXiv  Detail & Related papers  (2024-10-22T03:59:53Z)
• Large Language Models Know What Makes Exemplary Contexts [42.90814615222177]
  In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs) This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts.
  arXiv  Detail & Related papers  (2024-08-14T12:32:41Z)
• Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning [43.356895599336504]
  We analyze the working mechanisms of the learning-based demonstration selection methods. We empirically identify two important factors related to similarity measurement. We introduce two effective yet simplified exemplar selection methods catering to task-agnostic and task-specific demands.
  arXiv  Detail & Related papers  (2024-06-14T03:34:02Z)
• Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning [79.38140606606126]
  We propose an algorithmic framework that fine-tunes vision-language models (VLMs) with reinforcement learning (RL) Our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning. We demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks.
  arXiv  Detail & Related papers  (2024-05-16T17:50:19Z)
• Revisiting Demonstration Selection Strategies in In-Context Learning [66.11652803887284]
  Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL) In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent. We propose a data- and model-dependent demonstration selection method, textbfTopK + ConE, based on the assumption that textitthe performance of a demonstration positively correlates with its contribution to the model's understanding of the test samples.
  arXiv  Detail & Related papers  (2024-01-22T16:25:27Z)
• LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction [12.673710691468264]
  We introduce the Heuristic-Driven Link-of- Analogy (HD-LoA) prompting to address the challenge of example selection. Inspired by the analogical reasoning of human, we propose the link-of-analogy prompting, which enables LLMs to process new situations. Experiments show that our method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets.
  arXiv  Detail & Related papers  (2023-11-11T12:05:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.