Accepted Papers

Paper 3

When Should a Generative Agent Request Inspection? Cost-Sensitive Information Actions for Bridge Maintenance

Takayuki Shinohara

Paper 4

OpsBench: A Reliability-Oriented Benchmark for Open-Weight Agents on Internal Enterprise Operations

Willy Fitra Hendria

Paper 10

Cerebro: An Enterprise Language Model for Agentic Tool Use

Zixiang Chen, Sufeng Niu, Yingchi Liu, Wenting Zhao, Akshara Prabhakar, Shubham Mehrotra, Bin Bi, Zhujun Lan, Katherine Tan, Mohammad Ramezanali, Tulika Manoj Awalgaonkar, Monojit Banerjee, Jielin Qiu, Shiva Kumar Pentyala, Zhepeng Cen, Anupam Tripathi, Ali Ziaei, Regunathan Radhakrishnan, Darvish Lee Shadravan, Shelby Heinecke, Sitaram Asur, silvio savarese, James Zhu, Phil Mui, Huan Wang

Paper 12

From Enterprise Pipelines to Agent Context: Distilling Compact Models for Schema Lineage

Yi-Wei Chen, Jiaqi Yin, Meng-Lung Lee, Xiya Liu

Paper 14

Diversity by Construction: Grounded Question Generation for Agentic Commerce Memory

Mario Michael Krell, Ellen Ma, Sebastian Zuba, Marcus Yearwood

Paper 15

AgentFinVQA: An Auditable, On-Premise Multi-Agent Pipeline for Financial Chart QA

Aravind Narayanan, Shaina Raza

Paper 17

kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation

Kai Cheung, Lichi Li, Rohan Siva, Ganesh Sundaram, Shakthi Balasubramanian

Paper 18

Evidence Guided Adaptive Search for Helping AI Agents Find Missing Facts Before Answering

Akhil Kasturi, Min Cheng, Huilin Lu, Bingrou Zhou, Qiuying Lin, Ge Shi, Na Zhang

Paper 20

Stage: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control

Changjia Chen, Mengxi luo, An Cao, Zirong Huang, Wanyi Dai, Shixiong Gao, John Chen, Bo Wan

Paper 21

PointerBench: A Diagnostic Benchmark for Fine-Grained GUI Grounding

Valentino Sacco, Saurabh Pandey, Alexander Florian Jercher, Maximilian Schilling

Paper 22

Hallucination Detection in Black-Box LLMs Using Complementary Uncertainty Signals

Urja Pawar, Rajitha Ramanayake, Owen O'Neill, Nabeel Kemal, Abhishek Mandal, Houssem Chatbri, Christopher Martin

Paper 23

Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce

Zeyuan Li, Lukas Petersson, Alessandro Acquisti, Michiel A. Bakker

Paper 24

FiCo: Find-then-Compute for Corpus-Level Spreadsheet Question Answering

Sandarsita Guntupalli, Lu He, Kang Li

Paper 25

Esmeralda: A Benchmark for Enterprise Service Management Agent Readiness

Emily Chen, Patrice Bechard, Orlando Marquez Ayala, Manas Jiten Gandhi, Kavya Sriram, Jordan Skelton, Keerthana Gopinathan, Maggie Baird, Nidhi Kumari, Maria Kossenko, Ranjani Iyer, Roberto Bacci, Sagar Davasam, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar

Paper 27

CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents

Maxime Heuillet, Sharadind Peddiraju

Paper 28

Iterate on an LLM, Serve on an SLM

Keegan Wang

Paper 29

From Manuals to Worlds: Synthesizing Executable Enterprise Environments for LLM Agents

Harsh Vishwakarma, K.N Ajay Shastry, Pranoy Panda, Vartika Sengar, Ankush Agarwal, Suraj Mahadev Nagaje, Ganesh S, Shrey Satapara, Sanika Wagh, Pranav Bhagat, Mohit Meena, Ishan Jindal, Mahesh Chandran, Satoshi Nakashima, Hiromichi Kobashi

Paper 30

TS-AgentBench: Necessity vs. Robustness in Agentic Forecasting

Malik Tiomoko, Youssef Attia El Hili, Bahaeddine Abdessalem, Ding Wang, Dong Zhiwei, Zehao Xiao, Ambroise Odonnat, Shifeng Xie, Lei Zan, Jiale Zheng, Tareq Si Salem, Keli Zhang, Jianfeng Zhang, Lujia Pan

Paper 33

VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge

wenqi chen, Haofei Yang, Rui Yang, Li Fangming

Paper 35

Controlled Perturbation Reveals Grounding and Faithfulness Failures in Computer-Use Agents

Yangyue Wang, Harsh Sikka, Yash Mathur, Tony Zhou, Jinu Nyachhyon, Pranav Guruprasad

Paper 38

AgentScript-Eval: Benchmarking LLMs and Agents for Code Generation in an Enterprise DSL

Dipin Khati, Shubham Mehrotra, Bin Bi, Zhou Yu, Denys Poshyvanyk, James Zhu, Sitaram Asur, Phil Mui

Paper 39

Who’s Asking? A Role-Conditioned Benchmark for Operational Reasoning in Enterprise Agents

Trishala Jayesh Ahalpara, Jesica Bauer

Paper 41

Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?

Abhishek Pillai, Samir kumar nayak, Yuan Chen

Paper 42

AIM: Adversarial Interface Manipulation

Mareks Woodside, Lawrence Keunho Jang, Ruslan Salakhutdinov

Paper 43

Agentic Systems Need Multi-Run Evaluation: A Study of Retrieval and Response Variability in a Deployed Enterprise RAG System

Karan Gupta, Sumit Bhatia, Yunyao Li

Paper 44

Don't Prompt, Graph It: Reliable SOP Compliance via Workflow Graphs

Rahul Ghosh, Long Chen, Hari Prasanna Das, Divya Bhargavi, Vidya Sagar Ravipati

Paper 45

UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training

Ashish Jain, Armaan Sandhu

Paper 47

Can an Injected-Failure Benchmark Pick Your Monitor? A Four-Part Validity Audit for Enterprise Agent Deployment

Dev Utkarsh Pal, Arpan Verma, Chandan Sah, Aditya Upadhyay, Harshit Gupta

Paper 48

Break It to Align It: Preference Inversion for Domain-Specific Agents Safety Alignment

Seungyoun Lee, Seohyun Lee, Akihiro Sunagawa

Paper 49

From Document QA to Enterprise Tool Use: A Paired Outcome-and-Trajectory Study

Sushant Mehta

Paper 53

Agentic Search for Deployment-Specific Configuration of Promptable Detectors

Kyeongryeol Go

Paper 55

PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors

Himangi Mittal, Gaurav Mittal, Nelson Daniel Troncoso, Yu Hu

Paper 56

Where Does the Low-Cost Model Tier Break in Enterprise Agentic Workflows?

Zhenyu Zhang, Yuan Ling, Dingyang Chen, Xinyang Shen

Paper 58

Decoupled Planning and Execution for Trustworthy Agents in Closed-Environment

Monik Raj Behera, Preetam Keshari Nahak, Ajit Kumar Behera, Zahra Taghiyarrenani, Yuantao Fan, Thorsteinn S. Rögnvaldsson

Paper 60

Asymmetric Federated Agentic Intelligence

Olaf Yunus Laitinen Imanov, Rana Irem Turhan, Isgandar Jafarli

Paper 61

Constructing an Obligation-Aware Evaluation Corpus for Enterprise Agent Memory

Jayesh Rathi, Ananya Sane, Rajitha Ramanayake, Pradeep Nallathambi

Paper 62

Necessary or Sufficient? Evaluating Explanations from Enterprise LLM Decision Systems with Behavioural Interventions

Urja Pawar, Rajitha Ramanayake, Nabeel Kemal, Ashwin Kandath, Owen O'Neill, Guillaume Bourgeon, Houssem Chatbri

Paper 63

Enterprise-Scale Agentic Classification with a Governed Execution Envelope

Sruthi Pisipati, Haris Javed

Paper 64

EnterpriseFact: Where Frontier Agents Fail in Enterprise Fact-Finding

Md Shariq Farhan, Mohammad Imran Shaikh, Kunal Aggarwal

Paper 67

Determine: Benchmarking Graph-Driven Agentic Movie Making

Aayush Atul Verma, Hareesh Ravi, Ishan Rajendrakumar Dave, YZ Yang, Ajinkya Kale, Manuel Brack

Paper 69

Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability

Jeffrey Willette, Krishna C Puvvada, Boris Ginsburg

Paper 71

NovaMart: A Causally Consistent Simulated Enterprise for Measuring Tribal Knowledge Extraction

Susnato Dhar, Srijan Saket, Siddharth Seth, Rishabh Mehrotra

Paper 72

ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction

Sudha Priyadarshini, Mohamed Chahine Ghanem

Paper 73

VerifierContractBench: Auditing Safety Regressions in Evaluators for Enterprise Web Agents

Lakshya Narula, Saurabh Tripathi, Lily Bharati Sharma, Nikhil Rao

Paper 75

STRATA: Automated Construction of Professional Tasks and Rubrics for Agent Evaluation

Fenil Bardoliya, Shivali Dalmia, Abhishek Mukherji

Paper 76

BlueFin: Benchmarking LLM Agents on Financial Modeling

Srivatsa R Kundurthy, Clara Na, Colton Moraine, Anoushka Mohta, Case Winter, Jeremiah Giordani, Michelle Hui, Aashna Goel, George Fang, John Ling, Emma Strubell, Zach Kirshner

Paper 77

DockRepair: Evaluating Safe Abstention in Agentic Docker Compose Remediation

Nihanth Tatikonda, Sriram Gutlapalli, Apurva Reddy, Shanaya Pal, Lashika Kapoor

Paper 78

Taking the PULSE of Enterprise Workflows: Evaluating Persistent Project-State Understanding

Jiexin Ding, Lin Ai, Adam Davies, Scott Counts

Paper 79

Refusal Is Not Action Safety: Behavioral and Mechanistic Evidence from Tool-Using LLM Agents

Ekagra Gupta, Raj Saha, Adam Al Gharib, Aniekan-abasi Inyang

Paper 81

Verified Alt-Text for Product Catalogs: A Five-Agent Framework

Luis Miranda, Sergio Orellana, Daniel Alejandro Smith De La Carrera, Gonzalo Oyanedel-Vial

Paper 82

Can LLM Agents Remain Compliant Under Real-World Pressure?

Lanchen Song, Philippe Martin Wyder, Daniel Jaroslawicz, Judah Goldfeder, Karime Maamari

Paper 83

Evaluating LLM Agents on Multi-Modal Professional Finance Workflows

Jeremiah Giordani, Michelle Hui, Clara Na, Srivatsa R Kundurthy, Colton Moraine, Anoushka Mohta, John Ling, Zach Kirshner

Paper 84

Frontier Work: Benchmarking AI Agents on End-to-End Professional Workflows

Sushant Mehta

Paper 85

TOUMAII: A 4.5M-Pair Tool-Calling Preference Dataset and Its Source-Agnostic Generator

Moritz Pötzsch, Andrea Gentilini, Lisa Rossgoderer, Tom Osterfeld, Kesava Prasad Sanjivi Arul, Swanand Ravindra Kadhe

Paper 86

CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks

Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong, Abhishek Nagaraj

Paper 87

How Far Are Synthetic Text-to-SQL Benchmarks from Enterprise Production Traffic?

Victor Arantes, Thiago Pedroso de Jesus, Vinicius Alboneti Aguiar, Sávio Salvarino Teles de Oliveira

Paper 88

FORAGE: Related Works Prediction as a Benchmark for Agentic Retrieval

Aryaman Jain, Suvrat Bhooshan, Parth Sarthi

Paper 89

Unified Agentic Video Editing Across Levels of Complexity and Creativity

Surabhi S Nath, Kim Ferres, Milan Petrovic, Lion Schulz

Paper 90

SLATE: A Large-Scale Benchmark for Long-Horizon API Selection in Enterprise Tool Use

Ge Shi, Rongzhe Wei, Min Cheng, Leman Akoglu, Vaibhav Gorde, Sarthak Ghosh, Na Zhang, Pan Li

Paper 91

AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring

Chun Chet Ng, Zhen Hao Chu, Jia Yu Lim, Low Wei Zeng

Paper 92

PRISM: Prompt-Refined In-Context System Modeling for Financial Retrieval

Chun Chet Ng, Jia Yu Lim, Zhen Hao Chu, Yixi Zhou, Low Wei Zeng

Paper 93

When Guardrails Look Effective: Construct-Valid Evaluation for Multi-Agent Enterprise Commerce

Peiying Zhu, Sidi Chang

Paper 96

FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration

Weihang Ding, Junfei Zhan, Yueting Li, Qirong Guo

Paper 99

From LLM Control to Environment-Adaptive Agents: Sample-Efficient RL for Real-World HVAC Control

Toki Miyake, Hiroaki Murakami, Keiichiro Taniguchi, Katsuya Koike, Changyo Han, Shizuku Iida, Yoshihiro Kawahara

Paper 100

Deep Research Agents for Shell Company Screening

Feihan Lin, Xiao-Yang Liu

Paper 101

EnvOS: Certified Evaluation of Enterprise Agents in Changing Environments

Niharika singh, Athira Gopal, Ankush Kadu, Arpit Jain, Aswanth Krishnan

Paper 102

A Real-Robot Dataset for Multi-Stage Shoe Inspection Handling

Kazuki Takahashi, Shoichi Ohmoto, Hiroaki Murakami, Mitsuhiro Kamezaki, Yoshihiro Kawahara, Norimasa Kobori

Paper 103

Agentic Validation and Repair of Network Automation Programs with the Compiler as Judge

Zahra Bakhtiari

Paper 104

Westworld Finance Diligence Bench: Evaluating AI Agents on Long-Horizon Enterprise Work

Robert Alward, Alina Hyk, Victoria Knapp-Pérez, Wyatt Marshall

Paper 105

DEALTRACE: Localizing and Intervening on Failures in Agentic Financial Reasoning

Alina Hyk, Wyatt Marshall

Paper 106

WarehouseAI: A Closed-Loop Multi-Agent Framework for Industrial Operations Planning

Himabindu Thogaru, Anirudh Deodhar

Paper 107

CLAIMRECEIPT: Auditable Evidence Contracts for Enterprise Agent Benchmarks

Peiying Zhu, Sidi Chang

Paper 108

Towards continual in-context learning via training Cartridges at test time

Hongyi Huang, Kaitlyn Wang, Ajay Anubolu, Shayan Talaei, Arshia Soltani Moakhar, Azalia Mirhoseini, Amin Saberi