Interaction Dynamics as a Reward Signal for LLMs

📝 Original Info

• Title: Interaction Dynamics as a Reward Signal for LLMs
• ArXiv ID: 2511.08394
• Date: 2025-11-11
• Authors: 논문에 명시된 저자 정보가 제공되지 않았습니다. (예시: 김민수, 박지은, 이현우 등)

📝 Abstract

The alignment of Large Language Models (LLMs) for multi-turn conversations typically relies on reward signals derived from the content of the text. This approach, however, overlooks a rich, complementary source of signal: the dynamics of the interaction itself. This paper introduces TRACE (Trajectory-based Reward for Agent Collaboration Estimation), a novel reward signal derived from the geometric properties of a dialogue's embedding trajectory--a concept we term 'conversational geometry'. Our central finding is that a reward model trained only on these structural signals achieves a pairwise accuracy (68.20%) comparable to a powerful LLM baseline that analyzes the full transcript (70.04%). Furthermore, a hybrid model combining interaction dynamics with textual analysis achieves the highest performance (80.17%), demonstrating their complementary nature. This work provides strong evidence that for interactive settings, how an agent communicates is as powerful a predictor of success as what it says, offering a new, privacy-preserving framework that not only aligns agents but also serves as a diagnostic tool for understanding the distinct interaction patterns that drive successful collaboration.

💡 Deep Analysis

📄 Full Content

Reference