This paper proposes ToolCUA, an end-to-end agent designed to learn optimal GUI-Tool path selection through a staged training paradigm, and introduces an Interleaved GUI-Tool Trajectory Scaling Pipeline that repurposes abundant static GUI trajectories and synthesizes a grounded tool library, enabling diverse GUI-Tool tr...
Xuhao Hu, Xi Zhang, Hai-Yang Xu et al.· arXiv.org· 9 citations· ⚡4
CCTU, a benchmark for evaluating LLM tool use under complex constraints, is introduced and nine state-of-the-art LLMs are evaluated in both thinking and non-thinking modes, showing that models violate constraints in over 50% of cases.
Junjie Ye, Guoqiang Zhang, Wen-Jie Fu et al.· arXiv.org· 8 citations
On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood. We analyze the gradient of the per-token K2 estimator of reverse KL with respect to the student logits. The $\ell_1$...
Bing Shao, Jia-Zheng Zhang, Long Ma et al.· 5 citations
MuseCritic is introduced, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores, showing that critique-conditioned reward modeling reduces scoring error and provides an effective optimiza...
Jiabao Zhuang, Changhao Jiang, Hanchen Wang et al.· 0 citations
SPIEval is introduced, a human-curated benchmark grounded in five cognitive capabilities that exposes fundamental limitations of current LLM-based mobile assistants and motivates future research in this direction.
Junjie Ye, Zhuohui Sheng, Shao-Hua Liu et al.· 0 citations
A critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process and improves the actor’s exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger actor model.
Zhi-Heng Xi, Dingwen Yang, Jixuan Huang et al.· Proceedings of the Thirty-Fi...· 0 citations
This tutorial provides a comprehensive, end-to-end view of LLM interpretability, transitioning from microscopic neural analysis to macroscopic application and deployment, and explores how these interpretability paradigms scale and inspire the design of frontier architectures, agentic systems, and thinking models.
Wei Zhang, Zheng-Fu He, Lu-Lu Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
EntangleCodec is proposed, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization that achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding, and supports both TTS and TTA generation...
A novel textual representation of fault trees is proposed, and a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments is constructed, evaluating a model's ability to assist in malfunction localization.
Yuhui Wang, Zhi-Xiong Yang, Ming Zhang et al.· arXiv.org· 0 citations
CAFE (Coupled Agent--Feedback Evolution), a framework in which a shared-parameter model alternates between search-agent and critic roles, is introduced, suggesting that a self-improving search agent needs feedback that co-evolves with the policy it guides.
Bo-Yang Liu, Sen-Jie Jin, Pei-Xin Wang et al.· 1 citation
Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks.
Shi-Han Dou, Haoxiang Jia, Shichun Liu et al.· 1 citation
To mitigate a critical imbalance during the exploration-and-learning process, this work approaches head-tail re-balance during the exploration-and-learning process from two perspectives: distribution-reshaping and trajectory-resampling.
Xin Guo, Zhiheng Xi, Yiwen Ding et al.· Annual Meeting of the Associ...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
