JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making

cs.AI

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/HKUST-KnowComp/JockeyBench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
• CEO-Bench: Can Agents Play the Long Game?
• PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data
• Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
• KellyBench: A Benchmark for Long-Horizon Sequential Decision Making
• SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
• AIDE: AI-Driven Exploration in the Space of Code
• AI Agents That Matter
• BAGEN: Are LLM Agents Budget-Aware?
• Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making
• CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
• Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations
• Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
• Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems