A Survey on Multi-Turn Interaction Capabilities of Large Language Models
This post summarizes and annotates the survey paper "A Survey on Multi-Turn Interaction Capabilities of Large Language Models" (arXiv:2501.09959), published on 2025-01-17.
Overview
Multi-turn interaction in dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling coherent and contextually relevant responses. Recent advancements in large language models (LLMs) have significantly expanded the scope of multi-turn interaction, moving beyond chatbots to enable more dynamic agentic interactions with users or environments.
The survey provides a focused review of the multi-turn capabilities of LLMs, which are critical for downstream applications including conversational search and recommendation, consultation services, and interactive tutoring.
Four Key Aspects
1. Core model capabilities that contribute to effective multi-turn interaction; 2. Evaluation practices for multi-turn interaction; 3. General algorithms used to enhance multi-turn interaction; 4. Future research directions for the field.
Taxonomy of Related Methods
| Dimension | Sub-category | Representative approaches | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Bi-encoders, cross-encoders, DSI | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization objectives | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Diverges from real user satisfaction |
The field is commonly organized along four main lines: dense retrieval (high recall, low latency, suited to first-stage retrieval), late interaction (e.g., ColBERT; higher precision but larger indexes), generative IR (directly "generating" documents via tokens or docids, simplifying cascades), and agentic search (modeling search as sequential decision-making supporting multi-hop reasoning and self-reflection).
Research Timeline
- 2019–2021: BERT re-ranking and DPR establish neural retrieval foundations;
- 2022–2023: RAG and FreshLLM drive retrieval–generation fusion;
- 2024 onward: Conversational/agentic search and Gen-RecSys proliferate;
- 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth frontiers.
- Lack of unified benchmarks; private data not reproducible;
- LLM evaluation bias;
- Safety and cost constraints of agentic systems operating on the open web;
- Future work: finer-grained process supervision, joint retrieval–reasoning training, enterprise metadata governance, multimodal and cross-lingual consistency.
- Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey (arXiv:2503.22458)
- Beyond Whole Dialogue Modeling: Contextual Disentanglement for Conversation (arXiv:2504.17427)
- CHIQ: Contextual History Enhancement for Improving Query Rewriting (arXiv:2406.05013)
- Few-Shot Conversational Dense Retrieval, SIGIR 2021 (DOI: 10.1145/3404835.3462856)
Key Insights for Search / Recommendation / Personalization
1. Architecture: Cascaded retrieval + re-ranking + generation remains mainstream, but the agentic paradigm treats "when and how many times to retrieve" itself as a learnable object; 2. Data: High-quality instruction data and click/session logs are both critical; synthetic data must guard against knowledge leakage and distribution shift; 3. Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human evaluation; 4. Product: Latency, cost, interpretability, and safety are hard constraints for industrial deployment—academic benchmarks alone are insufficient.
Open Problems
Original Abstract
> Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large language models (LLMs) have significantly expanded the scope of multi-turn interaction, moving beyond chatbots to enable more dynamic agentic interactions with users or environments. In this paper, we provide a focused review of the multi-turn capabilities of LLMs, which are critical for a wide range of downstream applications, including conversational search and recommendation, consultation services, and interactive tutoring. This survey explores four key aspects: (1) the core model capabilities that contribute to effective multi-turn interaction, (2) how multi-turn interaction is evaluated in current practice, (3) the general algorithms used to enhance multi-turn interaction, and (4) potential future directions for research in this field.