# RecGPT-V2 Technical Report

arXiv: https://arxiv.org/abs/2512.14503 · HTML: https://mlsanity.com/paper/2512.14503/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge](https://mlsanity.com/paper/2506.21506/) (2025)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025)
- [Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models](https://mlsanity.com/paper/2505.02847/) (2025)
- [Meta Prompting for AI Systems](https://mlsanity.com/paper/2311.11482/) (2023)
- [RecGPT Technical Report](https://mlsanity.com/paper/2507.22879/) (2025)

## Built on by (most cited first, 8 of 8)

- [OneReason Technical Report](https://mlsanity.com/paper/2606.06260/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling](https://mlsanity.com/paper/2512.21257/) (2025)
- [RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems](https://mlsanity.com/paper/2602.12968/) (2026)
- [ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping](https://mlsanity.com/paper/2606.31693/) (2026)
- [WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models](https://mlsanity.com/paper/2607.26621/) (2026)
- [ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents](https://mlsanity.com/paper/2608.30685/) (2026)
- [Scaling Articulated Rationales for MLLM-based Recommendation](https://mlsanity.com/paper/2609.17639/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable potential in transforming recommender systems from implicit behavioral pattern matching to explicit intent reasoning. While RecGPT-V1 successfully pioneered this paradigm by integrating LLM-based reasoning into user interest mining and item tag prediction, it suffers from four fundamental limitations: (1) computational inefficiency and cognitive redundancy across multiple reasoning routes; (2) insufficient explanation diversity in fixed-template generation; (3) limited generalization under supervised learning paradigms; and (4) simplistic outcome-focused evaluation that fails to match human standards. To address these challenges, we present RecGPT-V2 with four key innovations. First, a Hierarchical Multi-Agent System restructures intent reasoning through coordinated collaboration, eliminating cognitive duplication while enabling diverse intent coverage. Combined with Hybrid Representation Inference that compresses user-behavior contexts, our framework reduces GPU consumption by 60% and improves exclusive recall from 9.39% to 10.99%. Second, a Meta-Prompting framework dynamically generates contextually adaptive prompts, improving explanation diversity by +7.3%. Third, constrained reinforcement learning mitigates multi-reward conflicts, achieving +24.1% improvement in tag prediction and +13.0% in explanation acceptance. Fourth, an Agent-as-a-Judge framework decomposes assessment into multi-step reasoning, improving human preference alignment. Online A/B tests on Taobao demonstrate significant improvements: +2.98% CTR, +3.71% IPV, +2.19% TV, and +11.46% NER. RecGPT-V2 establishes both the technical feasibility and commercial viability of deploying LLM-powered intent reasoning at scale, bridging the gap between cognitive exploration and industrial utility.