Mika Okamoto

† denotes equal contribution

1. CHI HCXAI

   

   Explainable Model Routing for Agentic Workflows

   Mika Okamoto, Ansel Erol, and Mark Riedl

   In Workshop on Human-Centered Explainable AI (HCXAI) at CHI, 2026

   Paper

   Agentic AI systems increasingly route subtasks across multiple specialized models, but these routing decisions are opaque to end users. We propose a framework for generating natural language explanations of model routing decisions in agentic workflows, enabling users to understand why tasks are delegated to specific models and supporting meaningful human oversight of automated multi-step pipelines.

   @inproceedings{okamoto2026explainable,
     venue_type = {workshop},
     title = {Explainable Model Routing for Agentic Workflows},
     author = {Okamoto, Mika and Erol, Ansel and Riedl, Mark},
     booktitle = {Workshop on Human-Centered Explainable AI (HCXAI) at CHI},
     year = {2026},
     note = {},
   }

2. CHI HCXAI

   

   Counterfactual Explanations for Agentic Workflows

   Madhuri Singh^†, Grace Kim^†, Mika Okamoto^†, Aarushi Ammavajjala, Amal Alabdulkarim, Gennie Mansi, and Mark Riedl

   In Workshop on Human-Centered Explainable AI (HCXAI) at CHI, 2026

   We introduce counterfactual explanation methods for multi-step agentic AI systems, providing users with actionable insights into how workflow outcomes could have differed under alternative conditions. Our approach generates counterfactuals that help users identify failure modes and build appropriate trust in automated agentic pipelines.

   @inproceedings{singh2026counterfactual,
     venue_type = {workshop},
     title = {Counterfactual Explanations for Agentic Workflows},
     author = {Singh, Madhuri and Kim, Grace and Okamoto, Mika and Ammavajjala, Aarushi and Alabdulkarim, Amal and Mansi, Gennie and Riedl, Mark},
     booktitle = {Workshop on Human-Centered Explainable AI (HCXAI) at CHI},
     year = {2026},
     note = {},
   }

3. ACL

   

   FLaME: Holistic Finance Language Model Evaluation

   Glenn Matlin^†, Mika Okamoto^†, Huzaifa Pardawala^†, Yang Yang, and Sudheer Chava

   In Findings of the Association for Computational Linguistics (ACL), 2025

   Paper Code

   We introduce FLaME, a comprehensive benchmark for evaluating large language models on a broad range of financial NLP tasks, including sentiment analysis, numerical reasoning, document understanding, and question answering. Our evaluation of frontier models reveals significant gaps between general LLM capabilities and the demands of real-world financial analysis.

   @inproceedings{matlin2025flame,
     venue_type = {conference},
     title = {{FLaME}: Holistic Finance Language Model Evaluation},
     author = {Matlin, Glenn and Okamoto, Mika and Pardawala, Huzaifa and Yang, Yang and Chava, Sudheer},
     booktitle = {Findings of the Association for Computational Linguistics (ACL)},
     year = {2025},
     note = {},
   }

4. MLSys

   

   Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing

   Mika Okamoto, Ansel Erol, and Glenn Matlin

   In MLSys Young Professionals Symposium (YPS), 2025

   Paper

   We introduce BELLA, a routing system that constructs interpretable skill profiles for LLMs to match incoming queries to the most capable and cost-efficient model. By making routing decisions transparent and grounded in empirically measured model competencies, BELLA achieves competitive task performance while reducing inference costs and providing users with clear rationale for model selection.

   @inproceedings{okamoto2025bella,
     venue_type = {workshop},
     title = {Trust by Design: Skill Profiles for Transparent, Cost-Aware {LLM} Routing},
     author = {Okamoto, Mika and Erol, Ansel and Matlin, Glenn},
     booktitle = {MLSys Young Professionals Symposium (YPS)},
     year = {2025},
     note = {},
   }

5. arXiv

   

   DeepVerify: Evidence-Based Expert-Level Scientific Claim Verification

   Siheng Xiong, Oguzhan Gungordu, Blair Johnson, Mika Okamoto, James C. Kerce, and Faramarz Fekri

   2026

   Code

   DeepVerify is an agentic framework for expert-level scientific claim verification, combining search, tool use, and structured reasoning to ground decisions in retrieved evidence.

   @misc{xiong2026deepverify,
     venue_type = {preprint},
     title = {DeepVerify: Evidence-Based Expert-Level Scientific Claim Verification},
     author = {Xiong, Siheng and Gungordu, Oguzhan and Johnson, Blair and Okamoto, Mika and Kerce, James C. and Fekri, Faramarz},
     year = {2026},
     note = {},
   }