Tagged articles
Self-Play
12 articles · Page 1 of 1
Two recent Peking University papers, VeriSkill and SESA, demonstrate that treating agent skills as self‑evolving memory—updated from failures via responsibility attribution, lesson abstraction, and failure distillation—yields significant performance gains across verification and search tasks and transfers across models.
AgentLLMProgram Verification
0 likes · 9 min read

The Deli AutoResearch SKILL, now open‑sourced, presents a three‑layer framework that tackles cognitive loops, stalling, and runtime fragility in long‑horizon tasks by persisting state, detecting stalls, and using a heartbeat watchdog, and it includes a paper‑writing skill with self‑play experiments that achieve self‑rated scores up to 8.6.
Long-Horizon TasksRL experimentsSelf-Play
0 likes · 17 min read

The paper introduces SE‑Bench, a code‑based benchmark that isolates knowledge internalization by obfuscating NumPy APIs, and uses it to reveal the Open‑Book paradox, the RL gap, and the potential of self‑play for true self‑evolution in large language models.
AIKnowledge InternalizationReinforcement Learning
0 likes · 17 min read


Amap TechJan 14, 2026 · Artificial Intelligence
Gaode Maps and Tongyi DeepResearch unveil ArenaRL, an open‑domain reinforcement‑learning framework that replaces absolute scoring with relative ranking, uses self‑play and a linear‑complexity tournament, and demonstrates measurable gains on POI ranking and complex travel‑planning tasks.
ArenaRLRankingReinforcement Learning
0 likes · 8 min read

This article examines the Language Self‑Play (LSP) approach for data‑free training of large language models, detailing its challenger‑solver game formulation, advantage calculations, loss functions, self‑reward extension, experimental setup on AlpacaEval, and results that show LSP can match or surpass data‑driven baselines.
LLMReinforcement LearningSelf-Play
0 likes · 14 min read

The author reviews Google NotebookLM, describing how it aids deep paper reading, boosts chat willingness with guided prompts, maintains conversation coherence through self‑play insights, highlights the audio‑overview feature, and reflects on AI concepts such as the "bitter lesson" and the limits of self‑play in open scenarios.
AI researchGoogleLLM
0 likes · 22 min read


ArchitectSep 28, 2024 · Artificial Intelligence
The article provides an in‑depth technical analysis of OpenAI’s multimodal o1 model, explaining its self‑play reinforcement‑learning pipeline, the novel train‑time and test‑time compute scaling laws, its long‑think reasoning abilities demonstrated through a cipher example, and speculative architectures for generator‑verifier systems.
OpenAIRL scalingSelf-Play
0 likes · 35 min read

This article reviews the evolution of game AI agents, examines how large language models (LLMs) can drive new AI behaviors in games, and discusses practical case studies across genres such as Werewolf‑style, war‑SLG, and MOBA games, concluding with challenges and future research directions.
AI agentsLLMLanguage Model
0 likes · 31 min read


Code DAODec 14, 2021 · Artificial Intelligence
This article walks through constructing a learnable chess AI by integrating AlphaZero‑style Monte Carlo Tree Search with a decoder‑only Transformer, detailing the game tree logic, model architecture, input and output encodings, self‑play training loop, and code implementation in PyTorch.
AlphaZeroMonteCarloTreeSearchPyTorch
0 likes · 23 min read

The paper presents DouZero, a reinforcement‑learning AI for the Chinese card game Dou Dizhu that combines a Monte‑Carlo method with a value network, uses binary matrix encodings for states and actions, and achieves human‑level play and state‑of‑the‑art results on modest GPU hardware.
AIDouZeroMonte Carlo
0 likes · 15 min read

After a nostalgic gaming session, the author recounts how Tencent’s upgraded AI, WeKick, leveraged self‑play reinforcement learning, GAIL‑based adversarial simulation, and a multi‑style League framework to dominate the inaugural Google Football Kaggle competition, illustrating the escalating complexity of multi‑agent AI in real‑time strategy games.
GAILKaggle competitionReinforcement Learning
0 likes · 8 min read

This article reviews the challenges of model‑free reinforcement learning, especially sparse reward issues exemplified by Montezuma’s Revenge, and surveys recent approaches such as expert demonstrations, curriculum learning, self‑play, hierarchical reinforcement learning, and count‑based exploration to mitigate these problems.
Model-freeSelf-Playcurriculum learning
0 likes · 12 min read
