| Title | : | Agentic Information Seeking for Knowledge Acquisition |
| Speaker | : | Dr. Revanth Gangi Reddy (Google DeepMind) |
| Details | : | Mon, 11 Aug, 2025 3:00 PM @ SSB 334 |
| Abstract: | : | The vast expansion of online information has shifted the challenge from simply locating data to efficiently filtering and aggregating relevant content from diverse sources. This talk introduces innovative methodologies aimed at enhancing automated information seeking capabilities within intelligent systems. I will present a modular, agent-based framework that decomposes the information-seeking process into navigation, extraction, and aggregation components, enabling exploratory behaviors that outperform current web agents. I will then discuss the application of this framework to the novel challenge of automatically updating Wikipedia. The second part of the talk focuses on enabling information-seeking over code repositories, wherein I will discuss our work on building state-of-the-art code embedding and ranking models directed at issue localization for addressing software problems. |
