9 papers
LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation
Fan Yang, Yuting Su, Xiaobo Wang +7
World-action modeling has emerged as a promising paradigm for robotic control, as it empowers models to go beyond reacting to observations and anticipate how a scene will evolve. H…
CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents
Zhaoyang Li, Zenghuang Fu, Qiuyuan Ai +6
Large language models can improve with reinforcement learning for search agents, yet existing self play agents repeatedly generate tasks while discarding the knowledge gained durin…
Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai +6
Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly…
Self-Supervised Skill Optimization
Siran Peng, Cuiyu Yang, Tianyu Fu +9
Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized with ground-truth (GT) feed…
Dive Into the Implicit Biases of Low-rank Vision-language Alignment
Mingjia Shi, Shuo Wang, Xiaobo Wang +7
Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requiring full-parameter updates.…
WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation
Wei Dong, Tianyu Fu, Zhe Yu +9
As web agents increasingly demonstrate capabilities in automated task execution, the development of robust evaluation frameworks for assessing their navigation and task completion…