Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks

arXiv:2610.05750 · cs.IR, cs.AI · Submitted 2026-10-05 · Read on arXiv

cs.IR, cs.AI

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/NVIDIA/NeMoRetriever

Terminology

• Agentic Retrieval — 1× in this paper · explained in 1 episode
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
• Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
• Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval
• The Faiss library
• TheMCPCompany: Creating General-purpose Agents with Task-specific Tools
• Query Expansion by Prompting Large Language Models
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios
• REPLUG: Retrieval-Augmented Black-Box Language Models
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• ReAct: Synergizing Reasoning and Acting in Language Models

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
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition