arXiv AI
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Choosing LLMs for Strategic Agent Interactions
arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabil...
arXiv Machine Learning
Aug 10
Solver-Guided Reasoning for Mixed-Equilibrium Strategies
arXiv:2608. 06741v1 Announce Type: new Abstract: Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales.
arXiv Machine Learning
Aug 12
Scaling Self-Play with Self-Guidance
arXiv:2604. 20209v2 Announce Type: replace Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together.
arXiv AI
Jun 2
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
arXiv:2606. 01561v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO).
arXiv AI
Sep 4
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
The paper introduces LUGL (Local Updates, Global Learning), a framework that separates data collection from model fitting, allowing non‑incremental learners such as gradient‑boosted trees (LightGBM) to be used in reinforcement learning for games. LUGL alternates between a local update phase—where agents play self‑play games and store tabular updates—and a global learning phase—where a function approximator is trained on the accumulated table before it is reset. Experiments on both perfect‑information and imperfect‑information games show that LightGBM‑based agents perform competitively or better than neural‑network baselines like DQN and DeepCFR.
arXiv Machine Learning
Jul 8
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.