From the 2 of 11 linked papers with an AI index.
11 papers
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Haojie Huang, Xinlei Yu, Chengming Xu +6
Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware pos…
Quo Vadis, World Modeling?
Yu Yang, Xuemeng Yang, Licheng Wen +17
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to paralleliz…
MemHarness: Memory Is Reconstructed, Not Replayed
Rong Wu, Daocheng Fu, Licheng Wen +10
The paper introduces MemHarness, a framework that lets large language model agents reconstruct and adapt retrieved past experiences to the current context instead of replaying them…
Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update
Daocheng Fu, Rong Wu, Yu Yang +7
The paper introduces PUST, a framework that uses a lightweight proxy model to explore high‑reward behaviors and then transfers the relative improvement signals to a larger primary…
IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing
Tao Hu, Jiaxin Ai, Licheng Wen +12
Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative re…
ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm
Jiaxin Ai, Tao Hu, Xuemeng Yang +11
Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumu…