CBRank, a Content-and-Behavior fusion learning to Rank framework, unifying content-based and behavioral signals within a pre-trained language model (PLM) to solve the “satisfaction-diverse” challenge of web search.
Yu-Chen Li, Hao Zhang, Yong-Qi Zhang et al.· IEEE Transactions on Knowled...· 0 citations
A preliminary study shows that verification has the strongest association with task success, but often occurs late, leaving limited opportunities for correction, and that the proportion of duty-relevant information decreases as records from different duties accumulate in a shared context.
Xue-Xin Shen, Lingyong Yan, Shuai-Qiang Wang et al.· 0 citations
PosterVisor is introduced, a control framework that shifts poster generation from transient prompts to persistent control and supports rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis.
Run-Ze Li, Yu-Kun Zhao, Can Xu et al.· 0 citations
This work proposes SCoRE (Selection and Consolidation for Robust Evidence), a unified agent loop for explicit evidence selection and consolidation, which decouples final reasoning from exploratory trial-and-error while ensuring strict visual grounding via indexed claim-to-image linkages.
Yucheng Shen, Lingyong Yan, Jiulong Wu et al.· 0 citations
This paper proposes SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing that combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance.
SAGE (Stability-Aware Gradient Efficiency), which maintains difficulty-stratified candidate pools refreshed during training and selects pairs within each pool by a forward-pass signal-to-curvature score, outperforms full-data and size-matched baselines while producing substantially smoother optimization trajectories.
Hui Wu, Hengyi Cai, Jin-Man Zhao et al.· 0 citations
DocOps is introduced, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy that deconstructs document operations inspired by real-world practices into atomic dimensions and escalating workflow complexities that exposes the capability boundaries of agents in maintaining global docum...
Jiazhen Jiang, Boxi Cao, Lingyong Yan et al.· arXiv.org· 1 citation
DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale production agent platform, is introduced, showing that performance under environmental perturbations is jointly shaped by the capabilities of the LLM and the surrounding agent framework.
Zechun Niu, Yu-Kun Zhao, Jia-Xin Zhang et al.· 1 citation
A lightweight training framework that learns a single Behavior-Equivalent Token that substantially reduces inference cost and frees nearly the entire context window for user inputs and model outputs.
Jiancheng Dong, Pengyue Jia, Jingyu Peng et al.· ACM International Conference...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.