Tagged articles
multi-turn dialogue
20 articles · Page 1 of 1

XikeSep 14, 2026 · Artificial Intelligence
This article explains intent recognition for AI agents, covering definition, common approaches (rules, LLM with structured output, semantic retrieval, hybrid), their pros and cons, suitable scenarios, and practical implementation advice including schema validation, confidence gating, and multi-turn handling.
AI agentsFunction CallingLLM
0 likes · 15 min read

Microsoft Research reveals that large language models excel on static single‑turn tasks but dramatically lose accuracy when user intent evolves across multiple turns, especially during function switches; the study formalizes three intent transition types, proposes a backward‑generation framework, and shows modest gains from memory mechanisms while highlighting the need for active intent recaps.
LLMMemory MechanismUser Intent
0 likes · 12 min read

This article explains how to use LangGraph's checkpoint and memory features together with a state‑machine router to build a chatbot that retains full conversation history, compresses long contexts, and dynamically switches between chat and task modes across multiple turns.
LangChainLangGraphMemory
0 likes · 5 min read

The ICLR 2026 Outstanding Paper awards spotlight two studies—one proving Transformers are mathematically succinct and another showing that all major LLMs lose about 39% performance in multi‑turn conversations, exposing a reliability gap missed by single‑turn benchmarks.
AI benchmarksICLR 2026LLM Evaluation
0 likes · 7 min read

Building a production‑grade multi‑turn dialogue agent requires managing LLM’s statelessness by combining sliding‑window and summary history, implementing three‑layer memory (working, short‑term, long‑term), using explicit state tracking with incremental JSON updates, optimizing context windows, orchestrating tool calls, and adding meta‑control to handle failures and prompt‑injection risks.
Context WindowLLMMemory System
0 likes · 18 min read

The article outlines practical methods for designing and refining prompts in multi‑turn conversations with large language models, covering task definition, contextual information, structured templates, step‑by‑step guidance, knowledge‑graph integration, dynamic adjustments, and real‑time data incorporation, each illustrated with concrete examples and code snippets.
AIcontextual promptinglarge language model
0 likes · 11 min read

Building a multi‑turn dialogue agent requires coordinated solutions for history management, layered memory, state tracking, context‑window optimization, tool‑call orchestration, and meta‑control, each addressing token limits, information relevance, and robustness, with practical strategies such as sliding windows, summarization, selective retention, and multi‑agent collaboration.
LLMMemory Architectureconversation agent
0 likes · 19 min read

This article breaks down the final‑mile challenges of Retrieval‑Augmented Generation—hallucinations, broken multi‑turn dialogue, prompt design, citation, and feedback loops—and provides concrete, layered solutions ranging from hard‑coded prompts and few‑shot examples to query rewriting, history management, post‑processing filters, and self‑check mechanisms.
RAGSelf-Checkcitation
0 likes · 15 min read

An MIT paper reveals that storing a language model’s own prior replies—known as context pollution—significantly lengthens the dialogue context while offering little quality benefit, with up to a ten‑fold reduction in tokens and comparable responses for about 70% of turns, especially in open‑source models.
AI agentsLLMMIT study
0 likes · 11 min read

CollabLLM tackles the limitations of large language models in everyday multi‑turn dialogues by introducing a user‑centric, multi‑turn training framework that leverages simulated interactions, multi‑round reward modeling, and veRL toolchain support, achieving superior performance over single‑turn baselines.
LLMcollaborative trainingmulti-turn dialogue
0 likes · 13 min read

This tutorial shows how to use LangGraph’s low‑level API to create a multi‑turn chatbot, define structured state, add model and tool nodes, implement conditional branching for tool calls, and reproduce a ReACT graph agent with a weather‑assistant example.
AI agentsLangGraphPython
0 likes · 12 min read

The article explains that large language models lose up to 35% performance in multi‑turn conversations, critiques static single‑turn evaluation methods, and proposes a dynamic user‑simulator with loss‑masking techniques to generate realistic test turns and improve assessment reliability.
AI testingLLMRLHF
0 likes · 6 min read

This article presents a comprehensive technical analysis of using large language models to build a task‑oriented multi‑turn dialogue system for intelligent marketing, detailing architecture, intent detection, slot extraction, prompt design, dialogue management, practical experience, and future research directions.
LLMintelligent marketingintent recognition
0 likes · 21 min read

This paper introduces Parrot, a system that enhances large language models' (LLMs) multi-turn instruction following capabilities through context-aware preference optimization (CaPO) and synthetic data generation, achieving significant performance improvements with limited training data.
CaPOData SynthesisNLP
0 likes · 9 min read

The 62nd ACL conference accepted four papers from Kuaishou that explore multi‑turn instruction following, self‑agreement reasoning, fine‑grained reinforcement learning, and dynamic routing in Mixture‑of‑Experts models, each with detailed methods, experimental results, author lists, and public arXiv links.
ACL 2024Kuaishou ResearchMixture of Experts
0 likes · 11 min read

This article explores how table‑based question answering can be integrated into B2B intelligent customer service by converting table queries into entity‑attribute recognition and multi‑turn dialogue, comparing end‑to‑end NL2SQL and slot‑filling approaches, and presenting NetEase Qiyu's practical implementation with its benefits and use cases.
Customer ServiceNL2SQLNLP
0 likes · 10 min read

Meituan’s intelligent customer service platform, serving over 630 million users and 7.7 million merchants, integrates six core AI capabilities—including problem recommendation, understanding, dialogue management, answer supply, response recommendation, and session summarization—across pre‑sale, in‑sale, after‑sale and internal scenarios, leveraging multi‑turn dialogue, intent recognition, knowledge‑graph Q&A, and the Moses platform, while targeting future end‑to‑end and emotionally intelligent interactions.
BERTDialogue SystemsTask Flow
0 likes · 23 min read


Didi TechOct 22, 2020 · Artificial Intelligence
The article reviews Didi’s research on a Multi‑turn Response Triggering Model (MRTM) that uses self‑supervised learning and asymmetric self‑attention to decide when a customer‑service chatbot should reply, achieving higher accuracy and recall than rule‑based and supervised baselines while remaining efficient enough for production deployment.
AICustomer ServiceSelf-Supervised Learning
0 likes · 12 min read

The article outlines the design and implementation of a multi‑turn conversational chatbot, detailing how natural‑language understanding converts user utterances into structured representations, a CNN‑LSTM language model classifies topics, intents, and sentiments, and an XML‑based answer engine orchestrates tasks and services for real‑world deployment.
AILanguage Modelchatbot
0 likes · 9 min read

The article presents a technical overview of Chatopera’s multi‑turn dialogue platform, covering language model fundamentals, Chinese segmentation, word embeddings, information retrieval, and open‑source tools, while illustrating how these AI techniques enable low‑cost, scalable enterprise chatbot solutions.
NLPinformation retrievalmulti-turn dialogue
0 likes · 11 min read
