PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Terminology
Sources
- Agentic Entropy-Balanced Policy Optimization
- From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
- The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- Selective Successor Eligibility Traces for RLVR
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
- StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- Qwen3 Technical Report
- Group Sequence Policy Optimization
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