CascadeRec: Deployed Adaptive LLM Compute Allocation for Multi-Tenant Content Recommendation
cs.IR, cs.AI, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/GuilinDev/llm-cascade-reranking
Terminology
Sources
- Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Setting
- Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- A Unified Approach to Routing and Cascading for LLMs
- BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
- Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- Large Language Models are Zero-Shot Rankers for Recommender Systems
- Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
- Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
- RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
- MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory
- RouteLLM: Learning to Route LLMs with Preference Data
- Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking
- LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems
- RobustExplain: Evaluating Robustness of LLM-Based Explanation Agents for Recommendation
- Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
- Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA