…Yifan Jiang , , , Abstract Affordance20Q benchmark challenges LLMs to infer object action possibilities through a 20-Questions game format without revealing object identities, revealing significant performance gaps compared to humans and identifying key…
…View arXiv page View PDF GitHub 27 Add to collection Community Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis…
…A deployment-relevant Text2Cypher benchmark therefore reflects the questions users and agents actually ask of that graph. Creating such a benchmark is difficult because schemas and values are unique, and graph structure…
…Ziwen Zhao , Abstract Ψ-RAG addresses limitations in tree-based retrieval-augmented generation for cross-document multi-hop questions through a hierarchical abstract tree index and multi-granular retrieval agent. AI-generated…
…Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While simply increasing the sampling budget for these questions is a common remedy, the static…
…when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience , and introduce…
…Single Presentation , which generates a single-speaker narrated presentation video; Discussion , which creates a multi-speaker presentation with structured speaker roles, such as for asking guiding questions, explaining concepts, clarifying details, and…
…To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains…
…Xinyue Cai , , , , Abstract An automated audio-visual question answering system uses entity-anchored video scripting and clue-guided QA generation to improve cross-modal reasoning and temporal consistency in video analysis. Generated…
…View arXiv page View PDF GitHub 7 Add to collection Community Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems…