pith. sign in

arxiv: 2501.09959 · v1 · pith:PS5FVZILnew · submitted 2025-01-17 · 💻 cs.CL

A Survey on Multi-Turn Interaction Capabilities of Large Language Models

classification 💻 cs.CL
keywords multi-turninteractioncapabilitiesdialoguelanguagelargellmsmodels
0
0 comments X
read the 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation

    cs.CL 2026-06 unverdicted novelty 7.0

    CRAB-Bench and RUSE create a new evaluation framework for LLM agents on constraint-graph tasks with realistic human-like user behaviors, reporting 61% pass@1 for the best model and up to 57% further drops under RUSE.

  2. ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

    cs.LG 2026-05 unverdicted novelty 7.0

    ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penal...

  3. MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

    cs.CR 2026-05 unverdicted novelty 6.0

    MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.

  4. MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation

    cs.CL 2026-04 unverdicted novelty 6.0

    MT-OSC condenses chat history via a one-off sequential process with a few-shot Condenser and lightweight Decider to reduce tokens and preserve LLM accuracy in multi-turn settings.

  5. Online Adaptive Probabilistic Safety Certificate with Language Guidance

    eess.SY 2025-11 unverdicted novelty 5.0

    A framework integrates user language and probabilistic environment estimates into adaptive safety certificates that guarantee long-term safety for stochastic systems via probabilistic invariance.

  6. From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

    cs.IR 2025-04 unverdicted novelty 5.0

    The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.

  7. A Framework for Longitudinal Health AI Agents

    cs.AI 2026-04 unverdicted novelty 4.0

    Proposes a multi-layer framework and agent architecture that operationalizes adaptation, coherence, continuity, and agency for longitudinal health AI agents.