{"total":56,"rows":[{"id":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","created":"2025-01-20","cited_by_count":400,"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":"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":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"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":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"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":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"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":"2506.08136","title":"EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2512.21720","title":"An Information Theoretic Perspective on Agentic System Design","created":"2025-12-25","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":"2511.07322","title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","created":"2025-11-10","cited_by_count":6,"area":"agents"},{"id":"2509.16369","title":"Enhancing Financial RAG with Agentic AI and Multi-HyDE: A Novel Approach to Knowledge Retrieval and Hallucination Reduction","created":"2025-09-19","cited_by_count":4,"area":"agents"},{"id":"2601.05039","title":"FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting","created":"2026-01-08","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":"2605.06472","title":"Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management","created":"2026-05-07","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":"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":"2608.14588","title":"The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2512.09440","title":"Knowledge-Augmented Large Language Model Agents for Explainable Financial Decision-Making","created":"2025-12-10","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":"2410.02823","title":"DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy","created":"2024-09-27","cited_by_count":2,"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":"2605.05538","title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2606.20629","title":"Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams","created":"2026-05-28","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":"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":"2607.27853","title":"FinanceHarness: Autonomous Financial Deep Research Framework","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2604.01221","title":"HippoCamp: Benchmarking Contextual Agents on Personal Computers","created":"2026-04-01","cited_by_count":1,"area":"agents"},{"id":"2604.14401","title":"Credo: Declarative Control of LLM Pipelines via Beliefs and Policies","created":"2026-04-15","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":"2608.04077","title":"FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.17718","title":"Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2510.07423","title":"ProSEA: Problem Solving via Exploration Agents","created":"2025-10-08","cited_by_count":0,"area":"agents"},{"id":"2604.09056","title":"Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout","created":"2026-04-10","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":"2605.27361","title":"Natural Language Query to Configuration for Retrieval Agents","created":"2026-05-26","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":"2606.08285","title":"Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"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":"2607.11141","title":"NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.20510","title":"Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain","created":"2026-07-04","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":"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":"2608.12984","title":"Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research","created":"2026-08-13","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":"2608.26114","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":"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":"2609.24002","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":"2609.33470","title":"LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.39958","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":"2610.09872","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}