This paper introduces a decentralized multi-agent decision-making framework for search and action problems under time constraints, treating time as a budgeted resource where actions have costs and rewards. The approach uses probabilistic reasoning to optimize decisions, maximizing reward within the given time. Evaluated in a simulated search, pick, and place scenario inspired by the Mohamed Bin Zayed International Robotics Challenge (MBZIRC), the algorithm outperformed benchmark strategies. Why it matters: The framework's validation in a Gazebo environment signals potential for real-world robotic applications, particularly in time-sensitive and cooperative tasks within the robotics domain in the UAE.
A delegation from the Abu Dhabi Executive Office (ADEO) Education Affairs Department visited MBZUAI on December 15, 2021. Ian Mathews, VP of Corporate Services, presented MBZUAI's progress and 2022 initiatives. Discussions covered the importance of collaboration and recruitment enhancements with ADEO's support. Why it matters: This visit highlights the ongoing relationship between MBZUAI and key Abu Dhabi government entities, signaling continued support for the university's AI initiatives.
This article discusses the need for a decentralized approach to AI, especially in contexts where data and knowledge are distributed. It highlights five key technical challenges: privacy, verifiability, incentives, orchestration, and crowdUX. The author, Ramesh Raskar from MIT Media Lab, advocates for integrating privacy tech, distributed verifiable AI, data markets, orchestration, and crowd experience into the Web3 framework. Why it matters: Decentralized AI could unlock new possibilities for collaboration and problem-solving in the region, particularly in sectors like healthcare and logistics where data is often siloed.
MBZUAI hosted a senior delegation from Iraq to discuss potential collaborations. The delegation toured the university campus and met with Provost Fakhri Karray. Discussions focused on MBZUAI's objectives, strategic plans, and opportunities for cooperative development between the UAE and Iraq. Why it matters: This visit signifies MBZUAI's ongoing efforts to foster AI development and collaboration across the Middle East.
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
A novel agent-based framework called FIRE is introduced for fact-checking long-form text. FIRE iteratively integrates evidence retrieval and claim verification, deciding whether to provide a final answer or generate a subsequent search query. Experiments show FIRE achieves comparable performance to existing methods while reducing LLM costs by 7.6x and search costs by 16.5x.