AnyStep World Action Model is introduced, a general framework for tunable-budget prediction and scene-dependent computation allocation and a lightweight risk-benefit scheduler predicts teacher-curvature-based difficulty and budget-specific student-teacher fidelity from a single one-step preview, selecting the smallest...
Rui Wang, Xiang-Yuan Wang, Dong-Lin Yang et al.· 0 citations
Meta-TTL is introduced, a framework that formulates the discovery of effective self-improvement policies as a bi-level optimization problem and consistently outperforms existing baselines, suggesting that the optimized self-improvement policy encodes transferable meta-strategies that generalize beyond the training task...
The ActiveArena-Sim, an active-perception simulator with controllable viewpoints and large-scale workspaces as the foundation, is introduced, and ActiveArena-Bench is proposed, which comprises 35 tasks across 5 fine-grained categories, covering visual exploration and interactive information acquisition.
Yi-Bo Li, En-Shen Zhou, Rui Chen et al.· 1 citation
This work proposes RealPref, a benchmark for evaluating natural preference-following in personalized user-LLM interactions, and finds that LLM performance drops significantly as context length grows and preference expression becomes more implicit, and that generalizing user preference understanding to unseen scenarios...
Qian-Yu Guo, Yi-Bo Li, Yue Liu et al.· 7 citations· ⚡1
This paper proposes PhysAgent, a reflective agentic framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair, and design a set of physics-control APIs to support more stable and complex motion behaviors.
Qirui Li, Jinkun Hao, Yibo Li et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
