Tag
Lune is a search engine built for scientific AI agents, connecting them to research knowledge and tools to deliver traceable, evidence-backed literature review, experimental design, writing, and peer review workflows.
This paper introduces Argus, an agent-based framework for persuasive argument generation that uses Theory-of-Mind to model audience beliefs, integrates rhetorical strategies and knowledge grounding, and demonstrates superior performance over baselines in evaluations.
OenoBench introduces a wine-domain benchmark for evaluating large language models on knowledge-grounded multiple-choice questions, built from verified sources to address limitations in existing benchmarks.
TeachMateGPT presents a multi-agent framework that improves retrieval-augmented generation for creating pedagogical assessments from science textbooks, achieving higher faithfulness and answer relevancy compared to baseline systems.
This paper introduces Regret Pre-training, a self-supervised framework that uses a dual-view architecture to incorporate future context into causal language model training, improving performance on downstream tasks by up to 18 percentage points without adding parameters.