Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
cs.IR, cs.AI
Submitted: 2026-09-01
Updated: 2026-09-02
Code: https://github.com/SCUNLP/DREAMS
Terminology
Sources
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era
- Evaluating Conversational Recommender Systems via Large Language Models: A User-Centric Framework
- SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search
- A Multi-Agent Conversational Recommender System
- A Large Language Model Enhanced Conversational Recommender System
- Leveraging Large Language Models in Conversational Recommender Systems
- Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
- Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors
- Lost in the Middle: How Language Models Use Long Contexts
- BARCOR: Towards A Unified Framework for Conversational Recommendation Systems
- Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue
- Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
- Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
- Vague Preference Policy Learning for Conversational Recommendation
- Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG