{"total":26,"rows":[{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2605.19337","title":"Agentic Trading: When LLM Agents Meet Financial Markets","created":"2026-05-19","cited_by_count":7,"area":"agents"},{"id":"2603.27539","title":"Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness","created":"2026-03-29","cited_by_count":5,"area":"agents"},{"id":"2511.13240","title":"Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions","created":"2025-11-17","cited_by_count":4,"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":"2605.14355","title":"Herculean: An Agentic Benchmark for Financial Intelligence","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2605.16895","title":"The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2606.06960","title":"FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2602.06486","title":"JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks","created":"2026-02-06","cited_by_count":2,"area":"agents"},{"id":"2602.09514","title":"EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies","created":"2026-02-10","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":"2608.30730","title":"E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation","created":"2026-08-31","cited_by_count":2,"area":"agents"},{"id":"2606.31522","title":"FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.18423","title":"FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents","created":"2026-08-19","cited_by_count":1,"area":"agents"},{"id":"2608.26226","title":"LLM Agents for Time-Series: A Survey","created":"2026-08-26","cited_by_count":1,"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":"2607.10286","title":"Can Agentic Trading Systems Pay for Their Own Intelligence?","created":"2026-07-11","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":"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":"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":"2609.33470","title":"LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","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":"2610.10407","title":"SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions","created":"2026-10-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}