Toward LLM Self-Play Under Data Scarcity: Effectiveness, Generalizability, and Trustworthiness
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- Process Reinforcement through Implicit Rewards
- InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
- Scaling Laws for Neural Language Models
- A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions
- ZeroGUI: Automating Online GUI Learning at Zero Human Cost
- An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders
- S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
- SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation
- The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
- Towards Agentic Self-Learning LLMs in Search Environment
- Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis
- VisPlay: Self-Evolving Vision-Language Models from Images
- Asymmetric self-play for automatic goal discovery in robotic manipulation
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
- SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
- Multi-Agent Evolve: LLM Self-Improve through Co-evolution
- Propose, Solve, Verify: Self-Play Through Formal Verification
- Meta-Learning Reinforcement Learning for Crypto-Return Prediction
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents