Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models

TMLR Paper7622 Authors

Abstract: Recent advances in large language models (LLMs) have substantially improved single-turn task performance, yet real-world applications increasingly demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent progress in evaluating and enhancing multi-turn LLM interactions. Centered on a task-oriented taxonomy—spanning instruction following in domains such as mathematics and coding, and conversational engagement in role-playing, healthcare, education, and adversarial jailbreak settings—we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness across prolonged dialogues. We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-context learning, supervised fine-tuning, reinforcement learning, and architectural innovations), external integration approaches (memory augmentation, retrieval-based methods, and knowledge graphs), and agent-based techniques for collaborative interaction. Finally, we identify open challenges and promising directions for future research to further improve the robustness and effectiveness of multi-turn LLM interactions.

Submission Type: Long submission (more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=7YELa9X7Td

Changes Since Last Submission: Page orientation is updated as requested.

Assigned Action Editor: ~Matthew_Walter1

Submission Number: 7622