An official website of the United States government
Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it is unclear how to complete a given task provably within a minimum number of interactions with the external environment, e.g., through an internal mechanism of reasoning. To this end, we propose the first framework with provable regret guarantees to orchestrate reasoning and acting, which we call “reason for future, act for now” (RAFA). Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon (“reason for future”). At each step, the LLM agent takes the initial action of the planned trajectory (“act for now”), stores the collected feedback in the memory buffer, and reinvokes the reasoning routine to replan the future trajectory from the new state. The key idea is to cast reasoning in LLMs as learning and planning in Bayesian adaptive Markov decision processes (MDPs). Correspondingly, we prompt LLMs with the memory buffer to estimate the unknown environment (learning) and generate an optimal trajectory for multiple future steps that maximize a value function (planning). The learning and planning subroutines are performed in an “incontext” manner to emulate the actor-critic update for MDPs. Our theoretical analysis establishes a √T regret, while our experimental validation demonstrates superior empirical performance. Here, T denotes the number of online interactions.
more »
« less
A Gridded Price-Adjusted Quantity Index for Total Production of Crops for Irrigated and Rainfed Farms for the Contiguous U.S.
Price-adjusted corn-equivalent index for total production and area for irrigated and rainfed farms for more than 75,000 grid cells over the continental United States calculated for years around 2010
more »
« less
- PAR ID:
- 10430127
- Publisher / Repository:
- MyGeoHUB
- Date Published:
- Edition / Version:
- 1.0
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
AI is beginning to transform every aspect of society. With the dramatic increases in AI, K-12 students need to be prepared to understand AI. To succeed as the workers, creators, and innovators of the future, students must be introduced to core concepts of AI as early as elementary school. However, building a curriculum that introduces AI content to K-12 students present significant challenges, such as connecting to prior knowledge, and developing curricula that are meaningful for students and possible for teachers to teach. To lay the groundwork for elementary AI education, we conducted a qualitative study into the design of AI curricular approaches with elementary teachers and students. Interviews with elementary teachers and students suggests four design principles for creating an effective elementary AI curriculum to promote uptake by teachers. This example will present the co-designed curriculum with teachers (PRIMARYAI) and describe how these four elements were incorporated into real-world problem-based learning scenarios.more » « less
-
Abstract Quantum technologies are poised to move the foundational principles of quantum physics to the forefront of applications. This roadmap identifies some of the key challenges and provides insights on material innovations underlying a range of exciting quantum technology frontiers. Over the past decades, hardware platforms enabling different quantum technologies have reached varying levels of maturity. This has allowed for first proof-of-principle demonstrations of quantum supremacy, for example quantum computers surpassing their classical counterparts, quantum communication with reliable security guaranteed by laws of quantum mechanics, and quantum sensors uniting the advantages of high sensitivity, high spatial resolution, and small footprints. In all cases, however, advancing these technologies to the next level of applications in relevant environments requires further development and innovations in the underlying materials. From a wealth of hardware platforms, we select representative and promising material systems in currently investigated quantum technologies. These include both the inherent quantum bit systems and materials playing supportive or enabling roles, and cover trapped ions, neutral atom arrays, rare earth ion systems, donors in silicon, color centers and defects in wide-band gap materials, two-dimensional materials and superconducting materials for single-photon detectors. Advancing these materials frontiers will require innovations from a diverse community of scientific expertise, and hence this roadmap will be of interest to a broad spectrum of disciplines.more » « less
-
This paper studies the evaluation of learning-based object detection models in conjunction with model-checking of formal specifications defined on an abstract model of an autonomous system and its environment. In particular, we define two metrics – proposition-labeled and class-labeled confusion matrices – for evaluating object detection, and we incorporate these metrics to compute the satisfaction probability of system-level safety requirements. While confusion matrices have been effective for comparative evaluation of classification and object detection models, our framework fills two key gaps. First, we relate the performance of object detection to formal requirements defined over downstream high-level planning tasks. In particular, we provide empirical results that show that the choice of a good object detection algorithm, with respect to formal requirements on the overall system, significantly depends on the downstream planning and control design. Secondly, unlike the traditional confusion matrix, our metrics account for variations in performance with respect to the distance between the ego and the object being detected. We demonstrate this framework on a car-pedestrian example by computing the satisfaction probabilities for safety requirements formalized in Linear Temporal Logic (LTL).more » « less
