One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning
cs.AI
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/xwsun01/AnySearch
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
- Token Economics for LLM Agents: A Dual-View Study from Computing and Economics
- SSRL: Self-Search Reinforcement Learning
- The Llama 3 Herd of Models
- Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
- Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
- Budget-Aware Tool-Use Enables Effective Agent Scaling
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
- A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
- BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
- A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Related papers
- 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
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection