{"total":30,"rows":[{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44,"area":"agents"},{"id":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2506.04098","title":"TextAtari: 100K Frames Game Playing with Language Agents","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2606.29771","title":"CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents","created":"2026-06-29","cited_by_count":6,"area":"agents"},{"id":"2512.00417","title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","created":"2025-11-29","cited_by_count":5,"area":"agents"},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.10015","title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.14355","title":"Herculean: An Agentic Benchmark for Financial Intelligence","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2512.02261","title":"TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?","created":"2025-12-01","cited_by_count":2,"area":"agents"},{"id":"2603.17694","title":"MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2606.26350","title":"OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents","created":"2026-06-24","cited_by_count":2,"area":"agents"},{"id":"2602.11304","title":"CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2604.04220","title":"TimeSeek: Temporal Reliability of Agentic Forecasters","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2608.23058","title":"LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.04667","title":"ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2512.02230","title":"Benchmarking LLM Agents for Wealth-Management Workflows","created":"2025-12-01","cited_by_count":0,"area":"agents"},{"id":"2604.26235","title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2606.08285","title":"Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2607.11141","title":"NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.25297","title":"Hybrid Analysis for Secure MCP Tool Use in LLM Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.09988","title":"OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.11232","title":"Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQs","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2609.00731","title":"Agentic Empirical Asset Pricing: Methodological Foundations","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.19705","title":"SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.35559","title":"From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00710","title":"ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.06748","title":"BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.09872","title":"LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets","created":"2026-10-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}