AI for Finance Summit 2026

Milan

The 3rd Workshop on LLMs and Generative AI for Finance

Next Generation of Generative AI Systems for Finance

Request a guest pass

ICAIF registration

Date

November 14 (Sat), 2026

Time

8:30 AM–6:00 PM CET

Location

Bocconi University, in the heart of Milan

Registration note: As part of ICAIF ’26, ticket registration is required and is managed on the main ICAIF conference site.
Please select the “AI for Finance: The 3rd Workshop on LLMs and Generative AI for Finance” workshop when registering. Ticketing questions: contact@ai4f.org.

AI for Finance Summit 2026

Milan

The 3rd Workshop on LLMs and Generative AI for Finance

Next Generation of Generative AI Systems for Finance

Request a guest pass

ICAIF registration

Date

November 14 (Sat), 2026

Time

8:30 AM–6:00 PM CET

Location

Bocconi University, in the heart of Milan

Registration note: As part of ICAIF ’26, ticket registration is required and is managed on the main ICAIF conference site.
Please select the “AI for Finance: The 3rd Workshop on LLMs and Generative AI for Finance” workshop when registering. Ticketing questions: contact@ai4f.org.

AI for Finance Summit 2026

Milan

The 3rd Workshop on LLMs and Generative AI for Finance

Next Generation of Generative AI Systems for Finance

Request a guest pass

ICAIF registration

Date

November 14 (Sat), 2026

Time

8:30 AM–6:00 PM CET

Location

Bocconi University, in the heart of Milan

Registration note: As part of ICAIF ’26, ticket registration is required and is managed on the main ICAIF conference site.
Please select the “AI for Finance: The 3rd Workshop on LLMs and Generative AI for Finance” workshop when registering. Ticketing questions: contact@ai4f.org.

The third edition builds on the 2024 (Brooklyn) and 2025 (Singapore) ICAIF workshops and focuses on the next generation of agentic, tool-augmented, retrieval-grounded, and governance-aware generative AI systems for high-stakes financial workflows.

The third edition builds on the 2024 (Brooklyn) and 2025 (Singapore) ICAIF workshops and focuses on the next generation of agentic, tool-augmented, retrieval-grounded, and governance-aware generative AI systems for high-stakes financial workflows.

About the Workshop

About the Workshop

The workshop moves beyond isolated model capabilities toward reliable institutional systems, covering agent orchestration, harness engineering, workflow-level evaluation, red teaming, retrieval and tool use, governance, auditability, model-risk management, and human-agent collaboration. Applications span investment research, compliance, credit, risk, ESG, reporting, surveillance, and quantitative strategies, supported by new datasets, benchmarks, and infrastructure.

As LLMs move from single-turn text generation toward agents that plan, retrieve, reason, use tools, and coordinate with humans, financial institutions face a new class of system-level challenges around reliability, auditability, compliance, and operational risk. The 2026 edition sharpens the focus on governed agentic AI systems for institutional finance: reliable, auditable, and deployable systems for real institutional workflows.

Thank you to our workshop sponsors

Thank you to our workshop sponsors

Thank you to our workshop sponsors

Qube Research & Technologies

Qube Research & Technologies

Qube Research & Technologies

qube-rt.com/

Standard Chartered

Standard Chartered

Standard Chartered

sc.com

sc.com

LinqAlpha

LinqAlpha

LinqAlpha

linqalpha.com

linqalpha.com

AQR Capital Management

AQR Capital Management

aqr.com

aqr.com

Speakers

Speakers

2026 Theme

Authority, Not Capability: Who Vouches for AI in Finance?

Authority, Not Capability: Who Vouches for AI in Finance?

Authority, Not Capability: Who Vouches for AI in Finance?

AI can now write the code, draft the research note and work through the mathematics. This year’s workshop asks what evidence, and whose judgment, makes those outputs safe to rely on for real financial decisions. Every session takes the same question: where do you still insist on a human, and why exactly there?

AI can now write the code, draft the research note and work through the mathematics. This year’s workshop asks what evidence, and whose judgment, makes those outputs safe to rely on for real financial decisions. Every session takes the same question: where do you still insist on a human, and why exactly there?

Keynotes

Huyên Pham

Huyên Pham

Professor of Applied Mathematics; President, Bachelier Finance Society

École Polytechnique

Rama Cont

Rama Cont

Professor of Mathematics; Head, Oxford Mathematical and Computational Finance Group

University of Oxford

Invited Talks

Raffaella Calabrese

Raffaella Calabrese

Chair of Statistics and Data Science

University of Edinburgh Business School

Mathieu Chalvidal

Mathieu Chalvidal

Quantitative Researcher

Capital Fund Management (CFM)

Panel 1

Buy-side

The Analyst and the Agent: LLM Agents That Read Filings, Earnings Calls and Broker Research

Analysts and portfolio managers on where agents now read disclosures and commentary for them, and where they still check every line.

  • Thierry Ciszewski
    Thierry Ciszewski
    Head of Equity Capability
    HSBC Asset Management
  • Jérôme Legras
    Jérôme Legras
    Managing Partner, Head of Research
    AXIOM Alternative Investments
  • Kurt Ze’ev Kara
    Kurt Ze’ev Kara
    Head of Global Value Equities & AI
    Maj Invest
  • Florian Sutter
    Florian Sutter
    Portfolio Manager
    la Mobiliare
  • Beatrice Cicerchia
    Beatrice Cicerchia
    Equity Strategist
    Intesa Sanpaolo

Panel 2

Sell-side

Signals and Sign-Offs: When Agents Propose, Code and Backtest Trading Signals

Quant heads on agents that generate signal ideas, write code and run backtests, how to tell a real signal from an overfitted one, and who approves it for live capital.

Moderator  Dr. Edward Tong, Google

  • Robert DeWitt
    Robert DeWitt
    Managing Director, Head of Quantitative Strategies Group
    Bank of America
  • Markus Ebner
    Markus Ebner
    Head of Multi Asset
    Quoniam Asset Management
  • Gianpaolo Tomasi
    Gianpaolo Tomasi
    Director, QIS Research
    Deutsche Bank
  • Maurizio Morini
    Maurizio Morini
    Financial Data Scientist
    Banca Aletti
  • Mishel Qyrana
    Mishel Qyrana
    Quant
    Generali Asset Management

Panel 3

Build-side

Built to Be Checked: Data Lineage, Permissions and Logs Behind Auditable AI Agents

Data and AI leaders from banks, asset managers and data providers on what must sit underneath an agent before a risk committee or supervisor accepts it.

  • Nicolas Moch
    Nicolas Moch
    Head of SEBx
    SEB
  • Alexander Horvat
    Alexander Horvat
    AI Solutions, Advisory & Financing Solutions
    UniCredit

More panelists to be announced.

Fireside

Who Signs Off? What a European Executive Has Allowed AI to Do, and What They Refused

Who Signs Off? What a European Executive Has Allowed AI to Do, and What They Refused

Who Signs Off? What a European Executive Has Allowed AI to Do, and What They Refused

A senior executive from a European institution on the decisions AI is trusted with today, and the ones it is not.

A senior executive from a European institution on the decisions AI is trusted with today, and the ones it is not.

Speaker to be announced.

Programme

Programme

Saturday, November 14, 2026, Main Hall, Bocconi University, 8:30 AM to 6:00 PM CET. Programme as of October 31, subject to change.

Saturday 14 November 2026, Bocconi University

08:30

Registration and coffee

08:50

Opening remarks

Jacob Choi, LinqAlpha

09:00

Keynote

Generative AI for Financial Dynamics: From Scenario Generation to Risk Decisions

Huyên Pham, École Polytechnique

09:40

Panel 1

The Analyst and the Agent

Buy-side

10:30

Coffee and Poster Session I

11:00

Invited talk

LLMs for litigation forecasting

Raffaella Calabrese, University of Edinburgh

11:20

Fireside

Speaker to be announced

11:50

Panel 2

Signals and Sign-Offs

Sell-side and quant

12:30

Oral papers I

Three peer-reviewed talks

  1. #60Do LLMs Understand Limit Order Book Dynamics? (Junxiao Chen)
  2. #91PALM: Point-in-Time Adaptation for Financial Language Models (Seunghan Lee)
  3. #80SHARP: Structured Hierarchical Agentic Reasoning for Corporate Bond Pricing (Ioana Baldini)
13:00

Lunch and Poster Session I (continued)

14:00

Invited talk

Risk in motion: large covariance estimation in the age of generative AI

Mathieu Chalvidal, Capital Fund Management

14:20

Panel 3

Built to Be Checked

Build-side

15:00

Oral papers II

Two peer-reviewed talks

  1. #107Deep Research Agents for Investment Surveillance in Information-Sparse Markets
  2. #63Buy the Rumor, Sell the News: When Is News Priced In? (Arman Khaledian)
15:20

Keynote

Keynote address, title to be announced

Rama Cont, University of Oxford

16:00

Coffee and Poster Session II

16:30

Oral papers III

Five peer-reviewed talks

  1. #99ZooBench: Localizing Failure in AI Replication of the Factor Zoo (Alejandro Canete)
  2. #123ClimInvestBench: Evaluating Agentic Investment Report Generation and Maintenance
  3. #113Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries (Radha Yadav)
  4. #75Correct but Unlicensed: Prompt Allowlists and the Traceability of Figures in LLM Financial Assistants (Hyeonwoo Jeon)
  5. #16Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent (Cosimo Galeone)
17:20

Closing remarks

17:30

Networking and Poster Session II

until 18:00

Programme as of 31 October 2026, subject to change.

Accepted Papers

Accepted Papers

Papers accepted to the 2026 workshop. Oral papers are presented in the main hall; all accepted papers are presented in the poster sessions.

Oral Presentations

01

Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent

Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent

Cosimo Galeone, Giuseppe Ettorre, Anna Ettorre, Ginevra Mariani, Minsu Park, Daniele Ligorio

02

Do LLMs Understand Limit Order Book Dynamics?

Do LLMs Understand Limit Order Book Dynamics?

Junxiao Chen, Paul Glasserman

03

Buy the Rumor, Sell the News: When Is News Priced In?

Buy the Rumor, Sell the News: When Is News Priced In?

Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini, Sid Ghatak, Arman Khaledian

04

Correct but Unlicensed: Prompt Allowlists and the Traceability of Figures in LLM Financial Assistants

Correct but Unlicensed: Prompt Allowlists and the Traceability of Figures in LLM Financial Assistants

Siddhesh Chaubal, Debarya Dutta, Hyeonwoo Jeon

05

SHARP: Structured Hierarchical Agentic Reasoning for Corporate Bond Pricing

SHARP: Structured Hierarchical Agentic Reasoning for Corporate Bond Pricing

Ni Ma, Chen-Tse Tsai, Yeu-Chern Harn, Chirag Gupta, Prabhanjan Kambadur, Ioana Baldini, David S Rosenberg, Camilo Ortiz

06

PALM: Point-in-Time Adaptation for Financial Language Models

PALM: Point-in-Time Adaptation for Financial Language Models

Seunghan Lee, Jun Seo, Jaehoon Lee, Junhyeok Kang, Sangjun Han, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Soonyoung Lee, Wonbin Ahn

07

ZooBench: Localizing Failure in AI Replication of the Factor Zoo

ZooBench: Localizing Failure in AI Replication of the Factor Zoo

Campbell Taylor, Sebastian Rivera, Sami Naeem, Alejandro Canete

08

Deep Research Agents for Investment Surveillance in Information-Sparse Markets

Deep Research Agents for Investment Surveillance in Information-Sparse Markets

Tianjiao Zhao, Jingrao Lyu, Kevin Zhao, Aslan Taheri, Marlin Brown, Tao Chen, Yueqi Wu, Dhagash Mehta

09

Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries

Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries

Radha Yadav, Prasanna Devadiga, Peeyush Mishra, Apoorv Singh

10

ClimInvestBench: Evaluating Agentic Investment Report Generation and Maintenance

ClimInvestBench: Evaluating Agentic Investment Report Generation and Maintenance

Edward Samuel Richards, Javier Sanz-Cruzado Puig, Richard McCreadie

Posters

11

A Discussion on Generative Preference Elicitation in Finance

A Discussion on Generative Preference Elicitation in Finance

Anagha Tiwari, Brian Jabarian, Alexander G. Gray, Nick Feamster, Alex Imas, Alex Kale

12

A Holistic Evaluation of Large Language Models for Earnings Forecasting

A Holistic Evaluation of Large Language Models for Earnings Forecasting

Yurun Sun, Pietro Panzarasa, Valentin Danchev

13

AI For Everyone: Measuring Assumptions and Mapping a Curriculum in Financial Services

AI For Everyone: Measuring Assumptions and Mapping a Curriculum in Financial Services

Nidhi Singh, Will Flanagan, Rajitha Ramanayake, Sarah Epstein, Ivan Wiryadi, Gisele DeWitt, Ananya Nagireddy, Ana Alfaro Pizana, James Usher

14

As-Of: Measuring Temporal Leakage in Retrieval-Grounded Financial Evaluation

As-Of: Measuring Temporal Leakage in Retrieval-Grounded Financial Evaluation

Jonathan Chang

15

Attribution Is a Propagation Problem in Multi-Agent Trading Systems

Attribution Is a Propagation Problem in Multi-Agent Trading Systems

Advije Rizvani, Giovanni Apruzzese, Pavel Laskov, Nils Lukas

16

BTFM: Learning and Transferring Financial Representations from Public Transaction Histories

BTFM: Learning and Transferring Financial Representations from Public Transaction Histories

Rodrigo Mendoza Smith

17

Can Personalized Advice Improve Investor Behavior? Evidence from a Multi-Agent Simulation of Retail Investors

Can Personalized Advice Improve Investor Behavior? Evidence from a Multi-Agent Simulation of Retail Investors

Yu Jeong Lee, Sujin Jung, Jaeho Jo, Junyoung Kwon, Sangjin Jin, Yongjae Lee

18

CLAIM: A Framework for Auditing LLM-Generated Financial Measures

CLAIM: A Framework for Auditing LLM-Generated Financial Measures

Xuan Yao, Kelvin J.L. Koa, Salsabila Fatma Aripa, Dai Yang, Yuxuan Tan, Zhou Yi, Ke-Wei Huang

19

Could This BE Any More Wrong? Teaching VLMs to Know What They Don’t Know in Document Extraction

Could This BE Any More Wrong? Teaching VLMs to Know What They Don’t Know in Document Extraction

Varad Srivastava, Prabhu R, Victor Daniel Casas Hernandez

20

Cross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic Screening

Cross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic Screening

Joong Ho Choi, Sherine George, Jiayang Zhao, Jayesh Rathi, Ashwin Kandath, Ananya Sane, Vishhvak Srinivasan

21

DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage

DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage

Ming Ze Tang, David Cutting, Boyd Carson, Vasiliki Carson

22

Decision-Focused Representation Adaptation for Cold-Start IPO Future-Peer Retrieval

Decision-Focused Representation Adaptation for Cold-Start IPO Future-Peer Retrieval

Yeonsuk Jung, Jang Ho Kim

23

Disagreement About Nothing: A Pre-Registered Stress Test of a Persona-Ensemble Measure of 10-K Complexity

Disagreement About Nothing: A Pre-Registered Stress Test of a Persona-Ensemble Measure of 10-K Complexity

Aryan Chhabra, Kuntara Pukthuanthong

24

Emergent Trading Biases in LLM Agent Swarms: Behavioral-Finance Benchmarks and Information-Channel Ablation

Emergent Trading Biases in LLM Agent Swarms: Behavioral-Finance Benchmarks and Information-Channel Ablation

Kian Jagtiani

25

Evaluating LLM-Directed Model Development: Lessons from Income Prediction

Evaluating LLM-Directed Model Development: Lessons from Income Prediction

Fang Fang, Alexander Statnikov

26

Extracting ESG Fields from Emerging-Market Sustainability Reports with LLM Assistants: A Pilot Evaluation on Kazakh and Uzbek Corporate Disclosures

Extracting ESG Fields from Emerging-Market Sustainability Reports with LLM Assistants: A Pilot Evaluation on Kazakh and Uzbek Corporate Disclosures

Feruza Kholmukhamedova

27

FinALTA: Deterministic Execution with Language-Model Explanations for Auditable Financial Question Answering over Budget Data

FinALTA: Deterministic Execution with Language-Model Explanations for Auditable Financial Question Answering over Budget Data

Areej AlOtaibi, Layali Abdulrahman Alsolami, Tasniem Nasser Alyahya

28

FinCausalAudit: Separating Error Detection from Evidence Use in Financial LLMs

FinCausalAudit: Separating Error Detection from Evidence Use in Financial LLMs

Maximilian Nicholson

29

FinPanel: Selecting LLM Trader Personas for Financial Trading

FinPanel: Selecting LLM Trader Personas for Financial Trading

Boming Yang, Yuquan Wang, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo

30

FINSABER-2: A Multimodal Benchmark for Comparing LLM Trading Agents with Passive and Quantitative Strategies

FINSABER-2: A Multimodal Benchmark for Comparing LLM Trading Agents with Passive and Quantitative Strategies

Feiyang Huang, Weixian Waylon Li, Yaxuan Kong, Mihai Cucuringu, Tiejun Ma

31

FiPARM: Financial Prompt Actionable Risk Management: A Governance Taxonomy for Prompt-Level Risk Classification in Financial Services

FiPARM: Financial Prompt Actionable Risk Management: A Governance Taxonomy for Prompt-Level Risk Classification in Financial Services

Owen O’Neill, Rajitha Ramanayake, Nicte Thorp, Urja Pawar, Abhishek Mandal, Houssem Chatbri, Christopher Martin

32

Firm-Level Energy Cost Exposure

Firm-Level Energy Cost Exposure

Zhang Zheng, Dong Xu

33

From Letter-of-Credit Requirements to Executable Specifications: Evaluating Verification Accuracy and Completeness

From Letter-of-Credit Requirements to Executable Specifications: Evaluating Verification Accuracy and Completeness

Ji Sub Choi, Whan Choi, Seo Yeon Gu, Kim Suhyun, Inyong Yun

34

Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy

Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy

Rian Dolphin, Joe Dursun, Jarrett Blankenship, Katie Adams, Quinton Pike

35

Honest Small Decision Models for Finance: Scale, Specialization Collapse, and Mixed-Corpus Remediation

Honest Small Decision Models for Finance: Scale, Specialization Collapse, and Mixed-Corpus Remediation

Ajitabh Kumar

36

Is All the Information in the Price? LLM Embeddings versus GICS and Price-Correlation Stock Clusters in a Factor-Model Test of the Efficient Markets Hypothesis

Is All the Information in the Price? LLM Embeddings versus GICS and Price-Correlation Stock Clusters in a Factor-Model Test of the Efficient Markets Hypothesis

Tucker Balch, Maria Hybinette, Grant Johnson, Bingyang Wang

37

LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline

LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline

Masoud Soleimani

38

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

Guanghao Wu, Zhuo Cai, Shoujin Wang

39

Multi-Agent LLMs for Replicating, Auditing, and Extending Corporate Bond Trading Strategies

Multi-Agent LLMs for Replicating, Auditing, and Extending Corporate Bond Trading Strategies

Zachary Alfalahi

40

Multidimensional Views Behind Target-Price Revisions: An LLM-Based Representation of Analyst Outlooks

Multidimensional Views Behind Target-Price Revisions: An LLM-Based Representation of Analyst Outlooks

Kiyoun Kim, Sung-Yeon Nathan Lim

41

One Shock, Many Voices: Do LLM Managers Discount Correlated Analyst Reports?

One Shock, Many Voices: Do LLM Managers Discount Correlated Analyst Reports?

Haotian Yang

42

Reading the Market: Portfolio Crash Prediction via Narrative Tracking and News-Coverage Bursts

Reading the Market: Portfolio Crash Prediction via Narrative Tracking and News-Coverage Bursts

Ziling Liu, Kelvin J.L. Koa, Ke-Wei Huang

43

Replicate the Decision, Not the Paragraph: An Executable Contract for Quantitative-Research Agents

Replicate the Decision, Not the Paragraph: An Executable Contract for Quantitative-Research Agents

Eric Benhamou, Jean-Jacques Ohan, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot

44

Semantic Lifting for Institutional Digital Asset Taxonomies: An Auditable LLM Workflow for DeFi Classification

Semantic Lifting for Institutional Digital Asset Taxonomies: An Auditable LLM Workflow for DeFi Classification

Hyunho Jeon, Seongchan Park, Byungsoo Kang, Gaeun Kim, Daehyun Kim

45

Ten Thousand Rows Is Not Enough: An Evaluation Protocol for Foundation-Model Return Signals

Ten Thousand Rows Is Not Enough: An Evaluation Protocol for Foundation-Model Return Signals

Kuan Ta Wu

46

The Determinism-Faithfulness Assurance Harness (DFAH): Evidence Before Execution in Financial Agent Gates

The Determinism-Faithfulness Assurance Harness (DFAH): Evidence Before Execution in Financial Agent Gates

Raffi Khatchadourian

47

The Expert and the Machine: A Case Study of Human-Steered and Autonomous Agents Iterating a Niche Domain Simulator

The Expert and the Machine: A Case Study of Human-Steered and Autonomous Agents Iterating a Niche Domain Simulator

Ollie Olby, Andreea Bacalum, Kibaek Lee, Namid Stillman

48

The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?

The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?

Jiayi Chen, Guiling Wang

49

Training Scores Are Not Returns: Workflow-Level Evaluation of LLM-Guided Alpha Search

Training Scores Are Not Returns: Workflow-Level Evaluation of LLM-Guided Alpha Search

Siyan Chen

50

Universal Diffusion Models for Implied Volatility Surfaces: Learning Shared Dynamics Across Stocks

Universal Diffusion Models for Implied Volatility Surfaces: Learning Shared Dynamics Across Stocks

Mingzhi Yang, Sheng Wang, Chao Zhang, Ruikun Li

51

Using LLMs for Table Data Extraction from Public Finance Documents

Using LLMs for Table Data Extraction from Public Finance Documents

Vikram Aggarwal, Siddarth Raman, Susan Thomas, Jay Kulkarni, Aakriti Narang, Aditi Mascarenhas, Ajay Shah

52

Verify Before You Sign: Benchmark Sensitivity and Tool-Output Deference in LLM Portfolio Advice

Verify Before You Sign: Benchmark Sensitivity and Tool-Output Deference in LLM Portfolio Advice

Nithilan Karthik, Arjun Subramanian

53

When Filings Are Silent: LLM News Readings and Volatility Forecasts Around Mergers

When Filings Are Silent: LLM News Readings and Volatility Forecasts Around Mergers

Donghwa Seo, Juyeong Lee, Doohwi Cha, Minsuk Sung, Minjae Lee, Seunghan Son, Yoontae Hwang

54

When Repeatable Labels Disagree: Prompt Reformulation in LLM Measurement of Financial Disclosures

When Repeatable Labels Disagree: Prompt Reformulation in LLM Measurement of Financial Disclosures

Hongzhen Du

55

When Should an LLM Agent System Change? Evidence-Gated Adaptation for Asset Allocation

When Should an LLM Agent System Change? Evidence-Gated Adaptation for Asset Allocation

Ali Atiah Alzahrani

56

Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron

Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron

Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong, Yongjae Lee

Format

Format

A full-day, in-person programme. All sessions are held on site.

01

01

01

Opening Remarks and Keynote Addresses (2 x 30 min)

Opening Remarks and Keynote Addresses (2 x 30 min)

02

02

02

Invited Talks (2 x 20 min)

Invited Talks
(2 x 20 min)

Invited Talks (2 x 20 min)

03

03

03

Industry Panels (3 x 40 min)

Industry Panels
(3 x 40 min)

Industry Panels (3 x 40 min)

04

04

04

Fireside Chat (30 min)

Fireside Chat
(30 min)

Fireside Chat (30 min)

05

05

05

Oral Paper Presentations (10 x 10 min)

Oral Paper Presentations
(10 x 10 min)

Oral Paper Presentations (10 x 10 min)

06

06

06

Poster Sessions and Closing Remarks

Poster Sessions and Closing Remarks

Poster Sessions and Closing Remarks

Key Dates

Key Dates

Paper Submissions

Paper Submissions

Submission Opens

Submission Opens

August 23, 2026

August 23, 2026

Submission Deadline

Submission Deadline

October 12, 2026 (Anywhere on Earth)

October 12, 2026 (Anywhere on Earth)

October 12, 2026 (Anywhere on Earth)

Author Notification

Author Notification

October 16, 2026 (Anywhere on Earth)

October 16, 2026 (Anywhere on Earth)

October 16, 2026 (Anywhere on Earth)

Workshop Day

Workshop Day

Workshop

Workshop

November 14, 2026 (Full-Day Session)

November 14, 2026
(Full-Day Session)

November 14, 2026 (Full-Day Session)

Location

Location

Main Hall, Bocconi University, Milan

Main Hall, Bocconi University, Milan

Call for Papers

Call for Papers

We welcome papers on generative AI and LLMs across both quantitative and discretionary fund contexts, with a 2026 emphasis on agentic, tool-augmented, and governed systems for institutional finance. Topics include but are not limited to:

Submit

Topics of Interest

Topics of Interest

01

Agentic and Multi-Agent Financial Workflows

Planning, coordination, and orchestration across specialized agents for investment research, compliance, credit analysis, financial reporting, risk management, ESG analysis, and market surveillance.

01

Agentic and Multi-Agent Financial Workflows

Planning, coordination, and orchestration across specialized agents for investment research, compliance, credit analysis, financial reporting, risk management, ESG analysis, and market surveillance.

02

Harness Engineering for Financial Agents

Execution scaffolds, evaluation harnesses, memory and state management, tool registries, permission control, intervention logging, and human escalation.

02

Harness Engineering for Financial Agents

Execution scaffolds, evaluation harnesses, memory and state management, tool registries, permission control, intervention logging, and human escalation.

03

Evaluation, Verification, and Red Teaming

Workflow-level benchmarks, process-level evaluation, numerical consistency, factuality, robustness, and failure analysis over regulated financial data.

03

Evaluation, Verification, and Red Teaming

Workflow-level benchmarks, process-level evaluation, numerical consistency, factuality, robustness, and failure analysis over regulated financial data.

04

Retrieval-Augmented and Tool-Augmented Systems

Retrieval architectures for financial corpora, structured-data querying, market-data integration, and tool-use patterns for research and compliance.

04

Retrieval-Augmented and Tool-Augmented Systems

Retrieval architectures for financial corpora, structured-data querying, market-data integration, and tool-use patterns for research and compliance.

05

Governance, Auditability, and Model-Risk Management

Compliance-aware deployment, intervention logging, escalation to human experts, and alignment with regulatory expectations across jurisdictions.

05

Governance, Auditability, and Model-Risk Management

Compliance-aware deployment, intervention logging, escalation to human experts, and alignment with regulatory expectations across jurisdictions.

06

Applications Across Financial Subdomains

Investment research, quantitative and systematic strategies, credit and fraud analysis, ESG and sustainability, market surveillance, financial reporting, and cross-border regulatory work.

06

Applications Across Financial Subdomains

Investment research, quantitative and systematic strategies, credit and fraud analysis, ESG and sustainability, market surveillance, financial reporting, and cross-border regulatory work.

07

Human-Agent Collaboration in Finance

Interaction patterns, oversight interfaces, escalation protocols, and workflow designs that balance agent autonomy with expert judgment.

07

Human-Agent Collaboration in Finance

Interaction patterns, oversight interfaces, escalation protocols, and workflow designs that balance agent autonomy with expert judgment.

08

Data, Benchmarks, and Infrastructure

New datasets, evaluation benchmarks, simulation environments, and open-source infrastructure for reproducible research on generative AI in finance.

08

Data, Benchmarks, and Infrastructure

New datasets, evaluation benchmarks, simulation environments, and open-source infrastructure for reproducible research on generative AI in finance.

Submission Guidelines

Submission Guidelines

There is no length limit or strict format requirement. Formatting according to ACM guidelines is recommended, but we encourage an open format so authors can focus on content. Submissions should be in PDF. The workshop is non-archival and will not have official proceedings.

Recommended formatting

Recommended formatting

01

01

ACM LaTeX Template (sigconf)

ACM LaTeX Template (sigconf)

02

02

ACM Word Template

ACM Word Template

Additional requirements:

Additional requirements:

  • For each submission, at least one author must agree to serve as a reviewer and deliver reviews on time.

  • The author list cannot be modified after the initial submission, except before printing.

  • Any changes after acceptance will be communicated directly with the authors.

After submission

After submission

After submission

Review process

Review process

Single-blind (authors known to reviewers, reviewers anonymous). No rebuttal period. All submissions treated with strict confidentiality.

Accepted papers

Accepted papers

All accepted papers are invited to the poster session (presenters print and bring their own posters); selected papers may get an oral slot. Non-archival: only author names and titles of accepted papers appear on the website.

Organizing Committee

Organizing Committee

Academia

Academia

Prof. Yoon Kim

MIT

Prof. Alejandro Lopez-Lira

University of Florida

Prof. Alvaro Cartea

University of Oxford

Prof. Sotirios Sabanis

University of Edinburgh Centre for Investing Innovation

Prof. Yongjae Lee

UNIST

Industry

Industry

Jacob Chanyeol Choi

LinqAlpha

Edward Tong

Google

Sina Molavipour

SEB

Alireza Javid

SEB

Didier Rodrigues Lopes

OpenBB

Fayssal El Mofatiche

Flowistic

Workshop Contact

Workshop Contact

Jacob Chanyeol Choi

LinqAlpha

contact@ai4f.org

contact@ai4f.org

contact@ai4f.org