collaborators

6 papers

cs.CL2026

TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents

Krishanu Adhikary, Prashant Devadiga

Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card,…

cs.AI2026

IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking

Suvradip Paul, Chandra Bhushan, Harsh Sharma +4

Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final response misses important erro…

cs.AI2026

FiMI Banking: A Sovereign Model for Indian Retail Banking

NPCI AI Research Team, Aman Kumar, Asit Desai +15

Banks need conversational systems that can answer product questions, assist customers with account-related requests, and operate safely within strict operational and regulatory con…

cs.AI2026

A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery

Prashant Devadiga, Abhishek, Adithya Mishra +9

The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registr…

cs.IR2026

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

Asit Desai, Aman Kumar, Prashant Devadiga

Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al…

cs.AI2026

FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem

Aboli Kathar, Aman Kumar, Anusha Kamath +37

We present FiMI (Finance Model for India), a domain-specialized financial language model developed by National Payments Corporation of India (NPCI) for Indian digital payment syste…