Cover Image

Scaling Self-Play with Self-Guidance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bailey, Luke, Wen, Kaiyue, Dong, Kefan, Hashimoto, Tatsunori, Ma, Tengyu
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
by: Dong, Kefan, et al.
Published: (2025)

Configuration-to-Performance Scaling Law with Neural Ansatz
by: Zhang, Huaqing, et al.
Published: (2026)

Pseudo-Formalization for Automatic Proof Verification
by: Barkallah, Slim, et al.
Published: (2026)

Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically
by: Dong, Kefan, et al.
Published: (2024)

Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
by: Mahankali, Arvind, et al.
Published: (2026)

Linguistic Calibration of Long-Form Generations
by: Band, Neil, et al.
Published: (2024)

Evaluating Self-Supervised Learning via Risk Decomposition
by: Dubois, Yann, et al.
Published: (2023)

Fantastic Pretraining Optimizers and Where to Find Them
by: Wen, Kaiyue, et al.
Published: (2025)

Scaling Laws for the Value of Individual Data Points in Machine Learning
by: Covert, Ian, et al.
Published: (2024)

Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective
by: Wen, Kaiyue, et al.
Published: (2024)

Observational Scaling Laws and the Predictability of Language Model Performance
by: Ruan, Yangjun, et al.
Published: (2024)

Language Models with Conformal Factuality Guarantees
by: Mohri, Christopher, et al.
Published: (2024)

A Bitter Lesson for Data Filtering
by: Mohri, Christopher, et al.
Published: (2026)

Understanding Finetuning for Factual Knowledge Extraction
by: Ghosal, Gaurav, et al.
Published: (2024)

Improving Pretraining Data Using Perplexity Correlations
by: Thrush, Tristan, et al.
Published: (2024)

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
by: Si, Chenglei, et al.
Published: (2024)

Pre-training under infinite compute
by: Kim, Konwoo, et al.
Published: (2025)

Synthetic Data for any Differentiable Target
by: Thrush, Tristan, et al.
Published: (2026)

Self-Improving AI Agents through Self-Play
by: Chojecki, Przemyslaw
Published: (2025)

Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning
by: Li, Shangzhe, et al.
Published: (2026)

Investigating Regularization of Self-Play Language Models
by: Alami, Reda, et al.
Published: (2024)

Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
by: Covert, Ian, et al.
Published: (2024)

$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
by: Zhang, Yaocheng, et al.
Published: (2026)

GASP: Guided Asymmetric Self-Play For Coding LLMs
by: Jana, Swadesh, et al.
Published: (2026)

The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
by: Si, Chenglei, et al.
Published: (2025)

Robust Distortion-free Watermarks for Language Models
by: Kuditipudi, Rohith, et al.
Published: (2023)

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
by: Tan, Zhewen, et al.
Published: (2026)

Diffusion Self-Weighted Guidance for Offline Reinforcement Learning
by: Tagle, Augusto, et al.
Published: (2025)

Non-Asymptotic Length Generalization
by: Chen, Thomas, et al.
Published: (2025)

Momentum Guidance: Plug-and-Play Guidance for Flow Models
by: Liao, Runlong, et al.
Published: (2026)

Offline Fictitious Self-Play for Competitive Games
by: Chen, Jingxiao, et al.
Published: (2024)

A Theoretical Framework for Self-Play Theorem Proving Algorithms
by: Chen, Thomas, et al.
Published: (2026)

Putting It All into Context: Simplifying Agents with LCLMs
by: Jiang, Mingjian, et al.
Published: (2025)

Data-efficient pre-training by scaling synthetic megadocs
by: Kim, Konwoo, et al.
Published: (2026)

On the Learnability of Watermarks for Language Models
by: Gu, Chenchen, et al.
Published: (2023)

Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
by: Dubois, Yann, et al.
Published: (2024)

Reasoning to Learn from Latent Thoughts
by: Ruan, Yangjun, et al.
Published: (2025)

Robust Autonomy Emerges from Self-Play
by: Cusumano-Towner, Marco, et al.
Published: (2025)

Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
by: Wang, Ru, et al.
Published: (2025)

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
by: Li, Gengsheng, et al.
Published: (2026)