כתבה
arXiv cs.AI ·
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
LLM Parkinsonism: תופעה של פעילות תמידית על אף פחתת ערך של המשימה, שפותרת על ידי ארכיטקטורת שליטה גלובלית (GEC).
תקציר מקורי באנגליתarXiv:2609.30662v2 Announce Type: replace Abstract: Large language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project-level executive control. Agents may continue acting after the original objective is satisfied, producing low-value refinements, repeated verification, and repairs to self-created complexity. We use LLM Parkinsonism as a narrowly defined, non-clinical metaphor for this pattern of persistent action despite diminishing task-level value. We argue that the problem is not explained by autoregressive next-token prediction alone, but more directly by concentrating proposal generation, scope interpretation, progress assessment, and stopping authority within the same self-conditioned loop. We there
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית