StreamDuo：一个实时解说员和一个研究智能体用于未见过的新游戏
StreamDuo: A Live Commentator and a Research Agent for Unseen Games
StreamDuo将一个可训练解说员与一个冻结的研究智能体配对，该研究智能体检索游戏维基条目，以在不针对目标游戏进行训练的情况下提高跨游戏直播解说。StreamDuo在 Baldur's Gate 3 上训练并在十个未见过的新游戏中测试，将实体召回率从 0.082 提高到 0.116，将源游戏泄露率从 9.9% 降低到 1.0%，并在直播模型中实现了最佳时机、最高的评判活力和总体质量。
Published on Oct 31
Authors:
,
,
,
,
,
Abstract
StreamDuo pairs a trainable commentator with a frozen research agent that retrieves game wiki entries to improve cross-game streaming commentary without training on target games.
Streaming video LLMs can now commentate live gameplay, but they are trained and tested on the same games. We study cross-game streaming commentary, in which a model trained on one game commentates games it has never seen, and find that current commentators transfer their timing but not their knowledge of the game world. We propose StreamDuo, which pairs a trainable commentator with a frozen research agent that reads the wiki of the game being played. When the commentator sees something it cannot name, it sends the current frames, and the research agent returns a few wiki entries two seconds later while the stream continues. We train only the commentator, on a single game, in two stages. Information-gain labels teach it to ask only where an answer would help it say what the human caster said, and on-policy self-distillation from a copy of itself that sees the ideal answer teaches it to use noisy answers. Trained on Baldur's Gate 3 and tested on ten unseen games, StreamDuo raises entity recall from 0.082 to 0.116 over Proact-VL trained on the same data, cuts source-game leakage from 9.9% to 1.0%, and achieves the best timing and the highest judged liveliness and overall quality among streaming models.
View arXiv page View PDF Project page GitHub 1 Add to collection
Get this paper in your agent:
hf papers read 2611.01120
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.01120 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.01120 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.01120 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源: Hugging Face Daily Papers · huggingface.co