At the start of every session, LLM agents load a fixed context file, such as $\texttt{AGENTS.md}$. Each loaded token in the file is charged again in every later round of the session, and these files can degrade performance as they grow in size. However, in practice, human or automated curators usually grow these files...
It is found that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms, and missed target windows.
Yi-Bo Ma, Qian-Qian Zhang, Peng Liu et al.· 0 citations
VLX-VR, an agentic-aware video reasoning model trained within a video reasoning framework defined by a Think--Memory--Observation loop, shows strong performance and broadly stable behavior across durations, while counting, state changes, causal reasoning, and spatial perception remain challenging.
Sheng Li, Peng Liu, Qian-Qian Zhang et al.· 0 citations
This work proposes an action-class-oriented diagnostic framework that decomposes multi-turn failures into two orthogonal modes: action-class miscalibration and action-execution failure.
Kangjia Zhao, Jia-Jun Li, Haozhan Shen et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
