mlsanityData to 14 Oct 2026

Towards AI Search Paradigm

arXiv 2506.17188 ↗First posted 20 Jun 2025cs.CL cs.AI cs.IRcited by 19

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular architecture of four LLM-powered agents (Master, Planner, Executor and Writer) that dynamically adapt to the full spectrum of information needs, from simple factual queries to complex multi-stage reasoning tasks. These agents collaborate dynamically through coordinated workflows to evaluate query complexity, decompose problems into executable plans, and orchestrate tool usage, task execution, and content synthesis. We systematically present key methodologies for realizing this paradigm, including task planning and tool integration, execution strategies, aligned and robust retrieval-augmented generation, and efficient LLM inference, spanning both algorithmic techniques and infrastructure-level optimizations. By providing an in-depth guide to these foundational components, this work aims to inform the development of trustworthy, adaptive, and scalable AI search systems.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 87 of its 167 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

87 of 167 references.

References · 87

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  9. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  10. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  11. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
38 more
  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  7. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  8. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  9. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  10. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  12. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  13. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 843
  14. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
  15. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  16. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  17. 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertaintycited by 578
  18. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
  19. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  20. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 384
  21. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  22. 2023SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verificationcited by 365
  23. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  24. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  25. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  26. 2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 326
  27. 2023Tool Learning with Foundation Modelscited by 302
  28. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  29. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 294
  30. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 279
  31. 2024Token-Budget-Aware LLM Reasoningcited by 247
  32. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 229
  33. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  34. 2025CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillationcited by 225
  35. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  36. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representationscited by 201
  37. 2024Mooncake: A KVCache-centric Disaggregated Architecture for LLM Servingcited by 196
  38. 2022Structured Pruning Learns Compact and Accurate Modelscited by 170

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 6.

19 papers.

Sort:

By area:

  1. 2025Search Self-play: Pushing the Frontier of Agent Capability without Supervisioncited by 34
  2. 2025Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoningcited by 17
  3. 2025Open Data Synthesis For Deep Researchcited by 16
  4. 2025AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learningcited by 8
  5. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 7
  6. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  7. 2025MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learningcited by 5
  8. 2026MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Searchcited by 5
  9. 2026FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decodingcited by 3
  10. 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledgecited by 3
  11. 2026DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoningcited by 2
  12. 2025Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generationcited by 1
7 more
  1. 2025REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimizationcited by 1
  2. 2026Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimizationcited by 1
  3. 2025R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platformscited by 0
  4. 2025Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkerscited by 0
  5. 2025A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecturecited by 0
  6. 2025Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoningcited by 0
  7. 2026SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
  2. 2025RAVine: Reality-Aligned Evaluation for Agentic Search
  3. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
  4. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  5. 2026SmartSearch: Process Reward-Guided Query Refinement for Search Agents
  6. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval
  7. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
  8. 2025Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents