LLM agents that operate over long inputs must perform context management: deciding what to retain in a fixed-size context window. A common approach is compaction, where the model replaces its history with a self-generated note. Yet off-the-shelf agentic models, including GPT-5.5 and GLM-5.3, often write ineffective not...
Yun-Fan Zhang, Taeho Hwang, Kathleen McKeown et al.· 0 citations
The DivAlgo benchmark is proposed, a large-scale dataset constituting algorithmically diverse solutions to programming problems that is significantly less diverse than human solutions and introduces a lightweight similarity metric to enable large-scale evaluation.
This work presents an automated framework that classifies suspected overdoses from death investigation reports, while producing supporting explanations guided by expert knowledge, and shows that a pipeline model with explanations grounded in the input death investigation reports outperforms the other settings.
Raavi Gupta, Zi-Qing Yang, Karli R. Hochstatter et al.· 0 citations
Human-centered artificial intelligence models that identify suspected overdose deaths using narrative reports from medicolegal death investigations and describe ethical considerations for using AI in overdose surveillance are developed and evaluated.
Karli R. Hochstatter, T. Nadel, Raavi Gupta et al.· American Journal of Public H...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.