בחינת סוכנים במסגרת חוזים רציפים: כאשר תחבולה עלולה לפגוע בעקביות או באיכות

תקציר מקורי באנגליתarXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python variables between actions; stateless runtimes clear them without resetting task progress. Training traces demonstrate task-solving strategies and runtime-specific ways to store and recover intermediate results. We study runtime transfer: whether agents trained under one contract remain effective under the other, a dependence that fixed-runtime evaluations can conceal. Across three tasks requiring a working record built from tool feedback, we fine-tune separate Qwen3-8B agents per task and runtime on instance-paired persistent and stateless traces and evaluate all four training-deployment combina