11 papers
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
Julian Killingback, Varad Ingale, Hamed Zamani +1
Late-interaction retrieval models that use the MaxSim similarity function have shown strong empirical performance, often outperforming single-vector dense and sparse retrieval mode…
RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
Mingchen Li, Hansi Zeng, Zhuo Qian +4
Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate queries, and search again. Tra…
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Hansi Zeng, Liam Collins, Bhuvesh Kumar +2
Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions -- has achieved remarkable pr…
TARSE: Test-Time Adaptation via Retrieval of Skills and Experience for Reasoning Agents
Junda Wang, Zonghai Tao, Hansi Zeng +3
Complex clinical decision making often fails not because a model lacks facts, but because it cannot reliably select and apply the right procedural knowledge and the right prior exa…
Scaling Laws for Embedding Dimension in Information Retrieval
Julian Killingback, Mahta Rafiee, Madine Manas +1
Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast…
Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?
Hansi Zeng, Kai Hui, Honglei Zhuang +4
While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size re…