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

**Authors:** Krishanu Adhikary, Prashant Devadiga  
**Lab:** National Payments Corporation of India · **Published:** 29 Sep 2026 · **Upvotes:** 11  
**Links:** [arXiv](https://arxiv.org/abs/2610.30161) · [PDF](https://arxiv.org/pdf/2610.30161) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.30161.html)

## Key numbers

- **1,000**: an action-oriented benchmark of 1,000 Indian retail-banking tasks where an assistant helps a simulated customer

## Abstract

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, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, such as obtaining a closure quote before closing a deposit. Adapting models to this domain requires measuring how well they follow the procedure, before and after training. Benchmarks usually judge only the records left at the end of a conversation. Many required steps, however, leave the records unchanged, so an assistant that skips them can still be judged successful. We present TauIndianBankBench, an action-oriented benchmark of 1,000 Indian retail-banking tasks where an assistant helps a simulated customer. Besides the final records, it checks that the assistant took every required step and made no unrequested change. For every model, 6.5-12.0% of sessions are judged successful when only the final records are checked, although the assistant skipped a required step or made an unrequested change. Scoring both procedure and outcome shows more accurately how well language models perform in Indian retail banking.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.