BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning

arXiv:2609.36505 · cs.AI, cs.LG, math.OC · Submitted 2026-09-29 · Read on arXiv

cs.AI, cs.LG, math.OC

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://jenniferquanxiao.github.io/BRIDGE/ABSTRACT

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Kimi K2: Open Agentic Intelligence
• Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
• Qwen2.5 Technical Report

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
• Agents' Last Exam
• 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