Learning Robust Social Strategies with Large Language Models
cs.LG
Submitted: 2025-11-24
Updated: 2026-10-30
Code: https://github.com/dereckpiche/AdAlignLLM
Terminology
Sources
- LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
- Best Response Shaping
- LOQA: Learning with Opponent Q-Learning Awareness
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- Evaluating Large Language Models Trained on Code
- Open Problems in Cooperative AI
- Evaluating Language Model Agency through Negotiations
- Advantage Alignment Algorithms
- Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- VinePPO: Refining Credit Assignment in RL Training of LLMs
- Deal or No Deal? End-to-End Learning for Negotiation Dialogues
- Efficacy of Language Model Self-Play in Non-Zero-Sum Games
- Model-Free Opponent Shaping
- Opponent Shaping in LLM Agents
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis