Searcharxiv⌕ Search

arXiv subjects

Mostapha Benhenda

Publications and source records attributed to Mostapha Benhenda.

7 recordsLinked to original sources
arXiv2026

IPO Finance Agent: Benchmark of LLM Financial Analysts Beyond Finance Agent v2, with Automated Rubric Generation, on the SpaceX (SPCX) IPO

Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks. However, it narrowly deals with periodic reporting from publicly traded companies (SEC 10-K and 10-Q filings), and its agentic harness relies on naive, unenriched chunk retrieval. Neither the task design nor the retrieval approach addresses the distinct challenges of IPO due diligence. SEC S-1 filings combine historical financial statements, governance structures, pro forma and common-control accounting treatments, capital-formation narratives, and underwriting-sensitive risk disclosures within substantially longer documents than typical periodic filings. That is why we introduce IPO Finance Agent, which extends the Finance Agent v2 framework along two directions: task domain and retrieval architecture. During our experiments, the original Finance Agent v2 harness basically failed to deliver any output related to the SpaceX S-1 filing, due to document length. We therefore had to improve the agentic harness with contextual retrieval, a more realistic and industry-standard approach for long documents. We also built a dataset of 1,000 IPO-diligence questions, and publicly release 70 questions on the SpaceX (SPCX) S-1 filing to support reproducibility, while the remainder are held private to guard against benchmark contamination. In addition, we introduce an evaluator-optimizer pipeline to automatically generate evaluation rubrics for the benchmark: candidate facts are extracted from model answers, consolidated into draft criteria, then automatically audited for omissions, hallucinations, mistiered items, and redundancy, with LLM feedback driving iterative repair, targeted enrichment, and deduplication. Human experts only review final rubrics before deployment. Results show that the best-performing evaluated model, Zhipu GLM-5.2, reaches 79.8% accuracy, and the most cost-efficient model on the resulting Pareto frontier, Xiaomi MiMo-2.5 Pro, reaches slightly lower accuracy (77.2%) at 0.05 USD per query, while exceeding the current Finance Agent v2 leaderboard ceiling, Google Gemini 3.5 Flash at 57.9% for 2.51 USD per query, and undercutting even FABv2's cheapest entry (MiniMax M3: 48.3% at 0.32 USD) on cost-efficiency. Code and data are released on GitHub https://github.com/benstaf/ipoagent

cs.AI↗
arXiv2026

Smooth Pseudo-Rotations Measure-Theoretically Isomorphic to Circle Rotations of Rationally Independent Angle

Let M be a smooth compact connected manifold, on which there exists an effective smooth circle action preserving a positive smooth volume. We show that on M, the smooth closure of the smooth volume-preserving conjugation class of some Liouville rotations of angle alpha contains a smooth volume-preserving diffeomorphism T that is metrically isomorphic to an irrational rotation of angle beta on the circle, with alpha different of beta, and with alpha and beta chosen either rationally dependent or rationally independent. In particular, if M is the closed annulus, M admits a smooth ergodic pseudo-rotation T of angle alpha that is metrically isomorphic to the rotation of angle beta. Moreover, T is smoothly tangent to the rotation of angle alpha on the boundary of M.

math.DS↗
arXiv2026

YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches

Forecasting startup success is notoriously difficult, partly because meaningful outcomes, such as exits, large funding rounds, and sustained revenue growth, are rare and can take years to materialize. As a result, signals are sparse and evaluation cycles are slow. Y Combinator batches offer a unique mitigation: each batch comprises around 200 startups, funded simultaneously, with evaluation at Demo Day only three months later. We introduce YC Bench, a live benchmark for forecasting early outperformance within YC batches. Using the YC W26 batch as a case study (196 startups), we measure outperformance with a Pre-Demo Day Score, a KPI combining publicly available traction signals and web visibility. This short-term metric enables rapid evaluation of forecasting models. As a baseline, we take Google mentions prior to the YC W26 application deadline, a simple proxy for prior brand recognition, recovering 6 of 11 top performers at YC Demo Day (55% recall). YC Bench provides a live benchmark for studying startup success forecasting, with iteration cycles measured in months rather than years. Code and Data are available on GitHub: https://github.com/benstaf/ycbench

cs.LG↗
arXiv2026

Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance

We introduce Look-Ahead-Bench, a standardized benchmark measuring look-ahead bias in Point-in-Time (PiT) Large Language Models (LLMs) within realistic and practical financial workflows. Unlike most existing approaches that primarily test inner lookahead knowledge via Q\\&A, our benchmark evaluates model behavior in practical scenarios. To distinguish genuine predictive capability from memorization-based performance, we analyze performance decay across temporally distinct market regimes, incorporating several quantitative baselines to establish performance thresholds. We evaluate prominent open-source LLMs -- Llama 3.1 (8B and 70B) and DeepSeek 3.2 -- against a family of Point-in-Time LLMs (Pitinf-Small, Pitinf-Medium, and frontier-level model Pitinf-Large) from PiT-Inference. Results reveal significant lookahead bias in standard LLMs, as measured with alpha decay, unlike Pitinf models, which demonstrate improved generalization and reasoning abilities as they scale in size. This work establishes a foundation for the standardized evaluation of temporal bias in financial LLMs and provides a practical framework for identifying models suitable for real-world deployment. Code is available on GitHub: https://github.com/benstaf/lookaheadbench

cs.AI↗
arXiv2025

FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents

This paper presents a novel risk-sensitive trading agent combining reinforcement learning and large language models (LLMs). We extend the Conditional Value-at-Risk Proximal Policy Optimization (CPPO) algorithm, by adding risk assessment and trading recommendation signals generated by a LLM from financial news. Our approach is backtested on the Nasdaq-100 index benchmark, using financial news data from the FNSPID dataset and the DeepSeek V3, Qwen 2.5 and Llama 3.3 language models. The code, data, and trading agents are available at: https://github.com/benstaf/FinRL_DeepSeek

q-fin.TR↗
arXiv2017

ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?

Generating molecules with desired chemical properties is important for drug discovery. The use of generative neural networks is promising for this task. However, from visual inspection, it often appears that generated samples lack diversity. In this paper, we quantify this internal chemical diversity, and we raise the following challenge: can a nontrivial AI model reproduce natural chemical diversity for desired molecules? To illustrate this question, we consider two generative models: a Reinforcement Learning model and the recently introduced ORGAN. Both fail at this challenge. We hope this challenge will stimulate research in this direction.

stat.ML↗