SEEDS: Preview-Guided Evidence Admission for Search Agents
cs.CL
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: 7 figures, 20 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
- GRASP: GRanularity-Aware Search Policy for Agentic RAG
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Active Retrieval Augmented Generation
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability
- From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation
- Proximal Policy Optimization Algorithms
- DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
- DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
- MuSiQue: Multihop Questions via Single-hop Question Composition
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- InfoAgent: Advancing Autonomous Information-Seeking Agents
- Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
- BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering