paper-with-me

Papers

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

2026-07-06 · Deyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong, Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, Yueyang Wang, Junfeng Zhong, Rui Liu, Tian Gao, Yangguang Lin, Jingyuan Zhang, Maojia Song, Xuan Qi, Jinhong Wu, Chenyang Zhang, Yinzhu Piao, Ziru Niu, Hongbin Lin, Lingxiang Meng, Peng Tang, Chengyao Tang, Shanyu Wu, Huanyu Zheng, Yu Liu, Liya Zhu, He Wang, Ming Ding, Ziyu Wan, Hao Liu, Sibo Wang, Haotian Zhu, Xintian Zhang, Nan Chai, Yipeng Liu, Panhao Lai, Sihang Yuan, Zixin Su, Ge Zhang, Wangchunshu Zhou, Yantao Du, Wenhao Huang, Guang Shi arxiv

Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less understood. Analyzing roughly 38,000 hours of agent interaction with the environment across 134 real world tasks, we find, to the best of our knowledge, the first evidence that overall performance during environment learning follows a log-sigmoid scaling law with remarkably high precision, reaching R^2 = 0.998. Across model generations, we also find that agent learning speed roughly doubles every three months. This discovery stems from EdgeBench, a suite of 134 real world tasks with ultra-long horizons, spanning scientific discovery, software engineering, combinatorial optimization, professional knowledge work, formal mathematics, and interactive games. Each task sustains at least 12 hours of continuous agent operation under rich, multilevel feedback, and is built through substantial expert effort. We publicly release 51 tasks and our full evaluation framework to accelerate the study of how agents learn from real world experience.

📄 PDF Abstract BibTeX arXiv:2607.05155

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian Neural Scaling Laws Extrapolation with Prior-Fitted Networks

2025-05-29 · Dongwoo Lee, Dong Bok Lee, Steven Adriaensen, Juho Lee 외

Scaling has been a major driver of recent advancements in deep learning. Numerous empirical studies have found that scaling laws often follow the power-law and proposed several variants of power-law functions to predict …

Active Learning

Unveiling Scaling Behaviors in Molecular Language Models: Effects of Model Size, Data, and Representation

2026-01-30 · Dong Xu, Qihua Pan, Sisi Yuan, Jianqiang Li 외 arxiv

Molecular generative models, often employing GPT-style language modeling on molecular string representations, have shown promising capabilities when scaled to large datasets and model sizes. However, it remains unclear a…

Bayesian scaling laws for in-context learning

2024-10-21 · Aryaman Arora, Dan Jurafsky, Christopher Potts, Noah D. Goodman

In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. Prior work has established strong correlations between the number of in-context examples pr…

In-Context LearningSafety Alignment

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws

2023-12-31 · Nikhil Sardana, Jacob Portes, Sasha Doubov, Jonathan Frankle

Large language model (LLM) scaling laws are empirical formulas that estimate changes in model quality as a result of increasing parameter count and training data. However, these formulas, including the popular Deepmind C…

Language ModelingLanguage ModellingLarge Language Model

Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers

2024-10-13 · Sheng-Chen Bai, Shi-Ju Ran

Interpreting the representation and generalization powers has been a long-standing issue in the field of machine learning (ML) and artificial intelligence. This work contributes to uncovering the emergence of universal s…