Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning

Documenti analoghi

• COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding
  di: Li, Xiaozhe, et al.
  Pubblicazione: (2026)
• ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding
  di: Li, Xiaozhe, et al.
  Pubblicazione: (2025)
• Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
  di: Li, Xiaozhe, et al.
  Pubblicazione: (2026)
• AutoContext: Instance-Level Context Learning for LLM Agents
  di: Cai, Kuntai, et al.
  Pubblicazione: (2025)
• Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
  di: Huang, Xijie, et al.
  Pubblicazione: (2023)