This work extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure, and validates SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic ind...
Xin-Nong Zhang, Jiayu Lin, Jia Wang et al.· 0 citations
JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF), achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems and supports a common factorized predictive principle across heterogeneous worlds.
Tao-Yong Cui, Zhong-Yao Wang, Xin-Yue Xu et al.· 2 citations
The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities.
He-Jia Geng, Ze-Sen Huang, Hao-Yang Li et al.· 3 citations
This work introduces and releases ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers'everyday workflows and presents case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scienti...
Shu-Han Xue, Jian-Yuan Zhong, Ziyuan Nan et al.· 2 citations
This work forms a unified approach to capability formation and process-centered evaluation, enabling discovery behavior to be trained, improved, and measured beyond final-answer performance.
Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales separately. We used a governed evolutionary AI Scientist to construct the Immune World Model, an action-conditioned model that learns how interventions move immune states...
Tao-Yong Cui, Xi Wang, Zong-Hang Li et al.· 0 citations
Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes, is introduced, a rolling benchmark covering 278 AI/ML fields and 1,390 episodes for large language models to track shifts in research attention.
Ying-Qian Wu, Jingcong Liang, Si-Yuan Wang et al.· 0 citations
Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history, positions recursively evolving memory as a scalable foundat...
Zhao-Chen Yu, Ying-Cheng Wu, Zhen-Fei Yin et al.· 4 citations
The PAST-Bench benchmark is introduced, a benchmark designed to isolate how persistent agents can progress from retaining experience to systematically improving through it, and Hermes+ is developed, which raises the average gain from retained experience and provides clearer pathway evidence.
Shu-Han Xue, Zixin Ding, Yi-Jun Shen et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
