Avi Sil

Title

Principal Research Scientist - Language and Agents
Avi Sil

Bio

Dr. Avi Sil is a Principal Research Scientist and a people manager at IBM Research AI. He has more than 10 years of experience in the field of AI and considered a global leader in the field of Retrieval Augmentation Generation and more recently on Agentic workflows. He leads the Multilingual Question Answering team (comprising of research scientists and engineers) and is the creator of the PrimeQA toolkit. His team's research has not only become products but also featured at the top of multiple leaderboards (Natural Questions, TyDI, XOR-TyDI).

He is a senior program committee member for major Computational Linguistics conferences including being an Area Chair several times. He has more than 20 US patents filed all in the area of Artificial Intelligence and it's applications in various spheres.

Research Interests: 

  • Agentic Workflows with LLMs
  • Inference Scaling algorithms with LLMs for GenAI applications
  • Retrieval Augmented Generation
  • Large language models and representation learning

Chair:

  • Virtual Infra Setup Chair:
    • ACL 2025
  • Industry Track Chair:
    • NAACL 2024

Latest News (selected topics)

  1. (new) Paper at ACL 2025 findings : SMART: Self-Aware Agent for Tool Overuse Mitigation. Joint work with UIUC NLP and Agentic lab.
  2. (new) Paper accepted at SIGIR 2025: A Large-Scale Study of Reranker Relevance Feedback at Inference.
  3. (new) Paper accepted at AAAI 2025 (Demo track): Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories.
  4. Paper accepted to TACL 2024 paper (presented at EMNLP) on a RAG dataset: CLAPnq: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems
  5. Paper accepted at EMNLP 2024: FIRST: Faster Improved Listwise Reranking with Single Token Decoding
  6. Paper accepted at ICLR 2024: Self-RAG (Joint work with Akari and Hanna from UW)