FanCric : Multi-Agentic Framework for Crafting Fantasy 11 Cricket Teams
Cricket, with its intricate strategies and deep history, increasingly captivates a global audience. The Indian Premier League (IPL), epitomizing Twenty20 cricket, showcases talent in a format that lasts just a few hours as opposed to the longer forms of the game. Renowned for its fusion of technology and fan engagement, the IPL stands as the world's most popular cricket league. This study concentrates on Dream11, India's leading fantasy cricket league for IPL, where participants craft virtual teams based on real player performances to compete internationally. Building a winning fantasy team requires navigating various complex factors including player form and match conditions. Traditionally, this has been approached through operations research and machine learning. This research introduces the FanCric framework, an advanced multi-agent system leveraging Large Language Models (LLMs) and a robust orchestration framework to enhance fantasy team selection in cricket. FanCric employs both structured and unstructured data to surpass traditional methods by incorporating sophisticated AI technologies. The analysis involved scrutinizing approximately 12.7 million unique entries from a Dream11 contest, evaluating FanCric's efficacy against the collective wisdom of crowds and a simpler Prompt Engineering approach. Ablation studies further assessed the impact of generating varying numbers of teams. The exploratory findings are promising, indicating that further investigation into FanCric's capabilities is warranted to fully realize its potential in enhancing strategic decision-making using LLMs in fantasy sports and business in general.
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks …
Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs
Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typicall…
FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework
Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level tasks and generalizing to unseen scenes. To …
Video GenerationFantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
Producing expressive facial animations from static images is a challenging task. Prior methods relying on explicit geometric priors (e.g., facial landmarks or 3DMM) often suffer from artifacts in cross reenactment and st…
Deep Artificial Intelligence for Fantasy Football Language Understanding
Fantasy sports allow fans to manage a team of their favorite athletes and compete with friends. The fantasy platform aligns the real-world statistical performance of athletes to fantasy scoring and has steadily risen in …
Articles