This work presents the first systems characterization of agent memory, introducing a system-oriented taxonomy classifying agent memory systems along four axes, and derives 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet...
MemoryArena is introduced, a unified evaluation gym for benchmarking agent memory in multi-session Memory-Agent-Environment loops with explicitly interdependent subtasks, where agents must learn from earlier actions and feedback by distilling experiences into memory, and subsequently use that memory to guide later acti...
This position paper argues that AI-assisted deliberation offers a more promising path by lowering barriers to meaningful engagement without substituting machine judgment for human choice.
José Ramón Enríquez, Jia-Xin Pei, A. Pentland· 0 citations
Learning from Hindsight is presented, which brings hindsight relabeling to RL post-training of VLAs by scoring failed rollouts against the tasks they actually achieved, and achieves 5 times improvement in sample efficiency, and outperforms a dense progress-reward baseline on out-of-distribution LIBERO-PRO tasks.
Iris Xu, Sunshine Jiang, John Marangola et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
