Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks an...
Jun-Xiang Wang, Yu-Chen Liu, Yi Wu et al.· 0 citations
Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verified, goal-specified research tasks spanning strong-field, attosecond, and neighboring physics areas. Each task specifies the research object...
Yi-Jia Mao, Song-Bin Dai, Tao Chen et al.· 0 citations
LLM-based multi-agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains. Recently, the dynamic orchestration of agent systems has become an important research direction. However, existing methods suffer from limited composition, misaligned dependencies, and inflexibl...
Jie Ren, Jiakang Yuan, Chen-Yu Huang et al.· 0 citations
ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This coupling makes action authorization and completion control difficult to enforce independently, allowing errors to propagate and unsupported completion claims to terminate...
Ajay Vohra, Tao Chen, Neeti Narayan et al.· 0 citations
LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of diversity in LLM post-training are mostly implicit, arising from general stochasticity and regularization mechanisms rather than explicitly targ...
Huai-Yu Fu, Heng Cao, Hao Wang et al.· 0 citations
This survey studies efficient GUI agents through an end-to-end systems lens that preserves the current technical axes of observation efficiency, context and memory efficiency, action efficiency, and planner-side/system efficiency.
Bizhe Bai, Jiakang Yuan, Hong-Zhou Wu et al.· 0 citations
This work introduces Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a dynamic skill controller that effectively bridges the gap between structured verification and open-ended exploration.
Siyuan Huang, Pengyu Cheng, Haotian Liu et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
