Synthèse
In a third environment, multi-objective question answering (from MEM1 Zhang et al., 2025, a recent work which performed end-to-end optimization in a modified version of typical recursive summarization), we demonstrate the utility of isolating belief states from reasoning, by showing that a Peak Belief length Penalty (more details in paper) significantly reduces memory usage with minimal performance degradation, unlike is commonly observed when penalizing reasoning lengths (Arora et al., 2025). F
In a third environment, multi-objective question answering (from MEM1 Zhang et al. , 2025, a recent work which performed end-to-end optimization in a modified version of typical recursive summarization), we demonstrate the utility of isolating belief states from reasoning, by showing that a Peak Belief length Penalty (more details in paper) significantly reduces memory usage with minimal performance degradation, unlike is commonly observed when penalizing reasoning lengths (Arora et al. , 2025). Fig. 7: Exact-match score and peak memory versus number of objectives in multi-objective QA.
ABBEL with a peak belief penalty (PBP) maintains comparable performance while using less memory than MEM1 and ABBEL without PBP in this evaluation.
Source originale
arxiv.org
CORTEX