PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
cs.CL, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting
- Multi-turn Reinforcement Learning from Preference Human Feedback
- Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement
- Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
- Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
- Personalization of Large Language Models: A Survey
- Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
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