PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

Documenti analoghi

• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework
  di: Zhang, Chao, et al.
  Pubblicazione: (2025)
• Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
  di: Liu, Shuochen, et al.
  Pubblicazione: (2025)
• VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
  di: Lin, Junda, et al.
  Pubblicazione: (2026)
• Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
  di: Xu, Derong, et al.
  Pubblicazione: (2026)
• FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
  di: Zhu, Junyi, et al.
  Pubblicazione: (2024)