10 papers
Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning
Bryan Wong, Xun Xu, Huazhu Fu +2
Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-free agentic frameworks formul…
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
Chengwei Wei, Jung-jae Kim, Longyin Zhang +2
Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing re…
SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series
Galann Pennec, Zhengyuan Liu, Nicholas Asher +2
We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize local understanding of adja…
The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation
Herun Wan, Jiaying Wu, Minnan Luo +4
Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts an…
MeMo: Memory as a Model
Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong +6
Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications req…
Is Data Shapley Not Better than Random in Data Selection? Ask NASH
Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +3
Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subset of data with top- Data Sh…