One Analyst Is Not Ground Truth: Grading Agent-Built Financial Models Against Observed Professional Practice
cs.LG, cs.AI, cs.CE
Submitted: 2026-07-27
Updated: 2026-09-26
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Fluid Language Model Benchmarking
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Kimi K2: Open Agentic Intelligence
- FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
- BlueFin: Benchmarking LLM Agents on Financial Spreadsheets
- gpt-oss-120b & gpt-oss-20b Model Card
- tinyBenchmarks: evaluating LLMs with fewer examples
- Seed1.8 Model Card: Towards Generalized Real-World Agency
- BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents
- LiveBench: A Challenging, Contamination-Limited LLM Benchmark
- Qwen3 Technical Report
- GLM-5: from Vibe Coding to Agentic Engineering
- From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks