Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events. In contrast, existing benchmarks focus on short- and medium-context tasks, and most foundation models struggle to preserve fin...
Yan-Hao Jia, Yi Zhu, Yi-Ran Zhong et al.· 0 citations
This work formalizes ScienceClaw as fixed-parameter program self-evolution that unifies task solving, scientific verification, and program updates and measures scientific correctness, evolutionary gain, retention, cross-dataset transfer, and evolution cost through sequential streams and independent reset evaluation.
Ming-Da Zhang, Wen-Jin Liu, Tiesunlong Shen et al.· 0 citations
Developing socially intelligent AI remains heavily dependent on human-annotated data, limiting the scale and breadth of social understanding models can acquire. Methods that derive training signals from unlabeled data offer a path beyond this dependence, but social predictions lack the verification oracles available in...
Keane Ong, Yuriel Ryan, Sabri Boughorbel et al.· 0 citations
The Affective Flow Language Model is proposed, which models multi-turn emotional support as an affective utility flow evolving along dialogue trajectories, providing a process-based approach to dynamic affect modeling and continuous strategy optimization.
Cheng Zou, Ning Wang, Tiesunlong Shen et al.· arXiv.org· 2 citations
MAGER is a multi-agent genetic evolution framework that automatically discovers meta-paths optimized for LLM reasoning, enabling frozen LLMs to perform structure-aware veracity reasoning and introduces a graph in-context learning strategy that retrieves semantically and structurally similar demonstrations to strengthen...
Zi-Yi Zhou, Xiao-Ming Zhang, Hui Pang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.