האם LLMs לומדים מפרסומים בתקציר? : חשיבה מחדש על תפקיד הפרסום בלמידה בתקציר

תקציר מקורי באנגליתarXiv:2610.11152v1 Announce Type: new Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often described as in-context reinforcement learning (ICRL). Whether in-context learning (ICL) can actually play the role of RL, however, has not been tested. We study this question in its simplest form, direct ICRL, where the model conditions directly on raw trajectory-reward pairs, and ask whether the reward acts as a learning signal. Through controlled experiments on four benchmarks across six models, we find that the reward is read, but its effect is small: flipping, randomizing, or removing the reward leaves the improvement curve almost unchanged, and this holds even under meta-prompts that explicitl