Search papers, labs, and topics across Lattice.
Johns Hopkins University
6
0
9
4
Programmatic skill learning can slash agent costs while enhancing performance, with SpeedRunner leading the charge in cost-efficient adaptation.
SelfCompact reveals that language models can autonomously manage context decay, achieving up to 18.1 points improvement in performance while cutting token costs by 30-70%.
Document LoRA can recover up to 21 ROUGE-L points when context is scarce, redefining its role in memory architecture for question answering.
Agentic harnesses can significantly enhance LLM performance on deontic reasoning tasks, but not without introducing risks of degradation in numerical accuracy.
Even state-of-the-art LLMs struggle to follow complex instruction hierarchies, achieving only ~40% accuracy when navigating conflicts across a dozen privilege levels in agentic tasks.
LLMs struggle to navigate the nuances of real-world rules, achieving only ~45% accuracy on a new benchmark of legal and policy reasoning tasks.
