Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging
cs.AI
Submitted: 2026-05-13
Updated: 2026-11-16
Code: https://github.com/vllm-project/vllm2https:
Terminology
Sources
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Deep Research Agents: A Systematic Examination And Roadmap
- A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
- Tongyi DeepResearch Technical Report
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Dr. Zero: Self-Evolving Search Agents without Training Data
- AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
- CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- GPT-4 Technical Report
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Qwen2.5-Coder Technical Report
- EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes
- Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks
- Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
- Proximal Policy Optimization Algorithms
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents