{"total":65,"rows":[{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"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":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2509.13160","title":"FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning","created":"2025-09-16","cited_by_count":27,"area":"lr"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2606.05661","title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","created":"2026-06-04","cited_by_count":17,"area":null},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2602.11685","title":"DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2607.04686","title":"ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents","created":"2026-07-06","cited_by_count":11,"area":"agents"},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2603.08262","title":"FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use","created":"2026-03-09","cited_by_count":10,"area":"agents"},{"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":"2606.03829","title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","created":"2026-06-02","cited_by_count":7,"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":"2605.09539","title":"TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2606.02859","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2512.14744","title":"VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation","created":"2025-12-12","cited_by_count":4,"area":"rag"},{"id":"2603.00285","title":"TraderBench: How Robust Are AI Agents in Adversarial Capital Markets?","created":"2026-02-27","cited_by_count":4,"area":"agents"},{"id":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","cited_by_count":4,"area":null},{"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":"2604.15151","title":"QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2605.14355","title":"Herculean: An Agentic Benchmark for Financial Intelligence","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2608.00155","title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","created":"2026-07-31","cited_by_count":4,"area":"agents"},{"id":"2608.11683","title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2602.04234","title":"When Does Multi-Agent Collaboration Help? An Entropy Perspective","created":"2026-02-04","cited_by_count":3,"area":"agents"},{"id":"2604.24668","title":"The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2608.06144","title":"FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2604.11304","title":"BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2606.13608","title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2607.19409","title":"FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance","created":"2026-07-11","cited_by_count":2,"area":"agents"},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2602.11304","title":"CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2606.03918","title":"Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.14747","title":"WANDR: A Benchmark for Wide and Deep Research","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2512.02230","title":"Benchmarking LLM Agents for Wealth-Management Workflows","created":"2025-12-01","cited_by_count":0,"area":"agents"},{"id":"2512.14717","title":"Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2602.05289","title":"Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2603.25342","title":"From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents","created":"2026-03-26","cited_by_count":0,"area":"agents"},{"id":"2604.22820","title":"Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows","created":"2026-04-17","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":"2605.02503","title":"DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2605.27466","title":"AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2606.00939","title":"FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation","created":"2026-05-31","cited_by_count":0,"area":"agents"},{"id":"2606.01886","title":"Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.11166","title":"Flaws in the LLM Automation Narrative","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.12871","title":"DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2606.23032","title":"IPO Finance Agent: Benchmark of LLM Financial Analysts Beyond Finance Agent v2, with Automated Rubric Generation, on the SpaceX (SPCX) IPO","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2606.26346","title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.20645","title":"Frontier Financial Judgement: Can agents tell what might move a stock?","created":"2026-07-22","cited_by_count":0,"area":"agents"},{"id":"2607.25656","title":"OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.28430","title":"AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2607.28661","title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.05864","title":"Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs?","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.16386","title":"Mint-Agent: Introducing Finance-Native Agentic Foundation Models","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.25325","title":"FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.24002","title":"FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.25192","title":"FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.35744","title":"FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null},{"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"}],"next_cursor":null}