9 papers
Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
Sidhaarth Murali, João Coelho, Jingjie Ning +3
Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., more parallel rollouts). Here we focus on breadth scal…
Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
João Coelho, João Magalhães, Bruno Martins +1
The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards. With these algorithms, a query contributes to parameter…
Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
Jingjie Ning, João Coelho, Yibo Kong +5
LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of how agentic search sessions un…
An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain
João Daniel Silva, Joao Magalhaes, Devis Tuia +1
The remote sensing community has recently seen the emergence of methods based on Large Vision and Language Models (LVLMs) that can address multiple tasks at the intersection of com…
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
João Coelho, Jingjie Ning, Jingyuan He +8
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most…
Multilingual Training-Free Remote Sensing Image Captioning
Carlos Rebelo, Gil Rocha, João Daniel Silva +1
Remote sensing image captioning has advanced rapidly through encoder--decoder models, although the reliance on large annotated datasets and the focus on English restricts global ap…