{"total":63,"rows":[{"id":"2510.16872","title":"DeepAnalyze: Agentic Large Language Models for Autonomous Data Science","created":"2025-10-19","cited_by_count":50,"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":"2505.16997","title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs","created":"2025-05-22","cited_by_count":38,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2407.06423","title":"InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation","created":"2024-07-08","cited_by_count":32,"area":"agents"},{"id":"2508.14052","title":"FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering","created":"2025-08-07","cited_by_count":29,"area":"agents"},{"id":"2406.06469","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","created":"2024-06-10","cited_by_count":16,"area":"agents"},{"id":"2510.11695","title":"When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents","created":"2025-10-13","cited_by_count":16,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2410.21741","title":"Enhancing Financial Question Answering with a Multi-Agent Reflection Framework","created":"2024-10-29","cited_by_count":12,"area":"agents"},{"id":"2605.28359","title":"From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets","created":"2026-05-27","cited_by_count":11,"area":"agents"},{"id":"2606.29955","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","created":"2026-06-29","cited_by_count":11,"area":"agents"},{"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":"2601.12259","title":"FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains","created":"2026-01-18","cited_by_count":9,"area":"agents"},{"id":"2505.12442","title":"IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems","created":"2025-05-18","cited_by_count":8,"area":"agents"},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2603.05520","title":"Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems","created":"2026-02-13","cited_by_count":8,"area":"agents"},{"id":"2510.20176","title":"Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding","created":"2025-10-23","cited_by_count":7,"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":"2506.08726","title":"Improved LLM Agents for Financial Document Question Answering","created":"2025-06-10","cited_by_count":5,"area":"agents"},{"id":"2509.14030","title":"CrowdAgent: Multi-Agent Managed Multi-Source Annotation System","created":"2025-09-17","cited_by_count":5,"area":"agents"},{"id":"2604.05966","title":"FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures","created":"2026-04-07","cited_by_count":5,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","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":"2605.29960","title":"Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction","created":"2026-05-28","cited_by_count":4,"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":"2501.12399","title":"FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools","created":"2025-01-08","cited_by_count":2,"area":"agents"},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2508.06418","title":"Quantifying Conversation Drift in MCP via Latent Polytope","created":"2025-08-08","cited_by_count":2,"area":"agents"},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","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":"2604.19548","title":"Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2605.10064","title":"MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2606.01351","title":"Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems","created":"2026-05-31","cited_by_count":2,"area":"agents"},{"id":"2509.09727","title":"A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs","created":"2025-09-10","cited_by_count":1,"area":"agents"},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2608.00764","title":"FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2609.10969","title":"Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2512.24314","title":"QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs","created":"2025-12-30","cited_by_count":0,"area":"agents"},{"id":"2603.09157","title":"Real-Time Trust Verification for Safe Agentic Actions using TrustBench","created":"2026-03-10","cited_by_count":0,"area":"agents"},{"id":"2605.08399","title":"CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2606.00189","title":"Learning to Construct Practical Agentic Systems","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.19416","title":"MortarBench: Evaluating Mortgage Loan Origination Agents","created":"2026-06-17","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":"2608.01772","title":"FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.06108","title":"Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.11381","title":"From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.16386","title":"Mint-Agent: Introducing Finance-Native Agentic Foundation Models","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.18099","title":"FinSkillBench: Evaluating AI Agents and Domain Skills for Investment Management","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2608.26114","title":"CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2608.27790","title":"Credo: Reusable Declarative Primitives for Agentic Workflows","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.05776","title":"DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.06059","title":"DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.21527","title":"OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"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":"2609.25237","title":"Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.28547","title":"PAWS: Policy-driven Agentic World Simulation","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.34225","title":"USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39958","title":"Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.13335","title":"AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.16661","title":"Structural Baselines Matter for Agent Failure Detection and Attribution","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17840","title":"Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}