The rapid proliferation of Generative AI (GenAI) into diverse, high-stakes domains necessitates robust and reproducible evaluation methods. However, practitioners often resort to ad-hoc, non-standardized scripts, as common metrics are often unsuitable for specialized, structured outputs (e.g., automated plans, time-series) or holistic comparison across modalities (e.g., text, audio, and image). This fragmentation hinders comparability and slows AI system development. To address this challenge, we present GAICo (Generative AI Comparator): a deployed, open-source Python library that streamlines and standardizes GenAI output comparison. GAICo provides a unified, extensible framework supporting a comprehensive suite of reference-based metrics for unstructured text, specialized structured data formats, and multimedia (images, audio). Its architecture features a high-level API for rapid, end-to-end analysis, from multi-model comparison to visualization and reporting, alongside direct metric access for granular control. We demonstrate GAICo's utility through a detailed case study evaluating and debugging complex, multi-modal AI Travel Assistant pipelines. GAICo empowers AI researchers and developers to efficiently assess system performance, make evaluation reproducible, improve development velocity, and ultimately build more trustworthy AI systems, aligning with the goal of moving faster and safer in AI deployment. Since its release on PyPI in Jun 2025, the tool has been downloaded over 16K times, across versions, by Dec 2025, demonstrating growing community interest.

The rapid evolution of Generative AI, yielding outputs across text, structured data, images, and audio, has outpaced the development of standardized evaluation tools, leading to fragmented and non-reproducible practices. GAICo (Generative AI Comparator) offers a solution: a deployed, open-source Python library that provides a unified, extensible, and reproducible framework for multi-modal GenAI evaluation. Our demonstration highlights GAICo’s utility through a practical case study: evaluating and debugging composite AI Travel Assistant pipelines. We show how GAICo facilitates isolating performance issues, for instance, distinguishing orchestrator LLM planning deficiencies from specialist image model generation flaws, by consistently comparing diverse outputs against tailored references. This framework streamlines development, improves system reliability, and promotes reproducible evaluation, making it a critical tool for building safer and more effective AI. Its rapid adoption, evidenced by over 16,000 downloads in the first 6 months, underscores its relevance and impact within the AI community.

Multi-Agent Path Finding (MAPF) algorithms provide highly optimized solutions for coordinating multiple agents in shared environments, yet their outputs lack explainability to human stakeholders. Existing explanation approaches, such as visual trace segmentation or logic-based reasoning, remain fragmented. In this demo, we present OMEGA, an interactive explanation platform that generates Natural Language (NL) explanations using the novel Multi-Agent Planning Ontology (maPO). Our framework transforms raw MAPF planner execution logs into a semantic knowledge graph, enabling SPARQL-based explanations of collision events, replanning strategies, and efficiency trade-offs. A lightweight web interface allows users to query, visualize, and interpret planner decisions, thereby making MAPF solutions transparent and auditable. We conducted a user study that confirms the ontology-driven explanations are significantly clearer and more preferred than raw logs, underscoring the potential of semantic technologies for explainable multi-agent systems.

In this student paper, we report on our project to enhance road safety in South Carolina (SC) by analyzing traffic data provided by the Department of Transportation and evaluating the impact of a school-level student driver education program called Alive@25. We improve the understanding of road safety using these traffic and training data to understand collision patterns and areas for improvement and assess training coverage gaps. Our approach combines geospatial analysis, economic impact assessment, temporal trend analysis, and interactive visualizations while leveraging AI techniques to clean and analyze extensive datasets. Key findings revealed higher collision rates in urban counties and rising collision rates in mostly rural areas, where Alive@25 participation is declining. These insights led to recommendations for improving road infrastructure and expanding safety training programs. This research demonstrates the potential of AI-driven insights to inform timely, cost-effective interventions and promote multi-stakeholder engagement in addressing public safety challenges while teaching students data science and AI skills and civic engagement.

In this blue sky paper, we seek to stimulate the research community to pursue important new as well as existing (unsolved) AI problems in the context of a challenging, often ignored, socio-sensitive application domain. We outline the key challenges in conducting elections credibly in leading democracies around the world today and identify our vision of a path forward with an overarching goal to increase voter participation with a two-pronged approach of AI-lead technological innovations and interdisciplinary community building. On the technology front, we envisage the need to transform Collation and Distribution of election information, and promote its Comprehensibility for users understanding and trust (CDC). On the community front, we need to invigorate the multi-disciplinary community consisting of, but not limited to, researchers in AI, security, journalism, political science, sociology, and business, to PROMote AI's Safe usage for Elections (PROMISE) with best-practices. This work is informed by our interdisciplinary research as well as experience in conducting three workshops at leading AI conferences and the AI Magazine special issue on AI and Elections.

Tracking the rapidly evolving literature at the intersection of large language models (LLMs) and planning has become increasingly complex due to significant growth in research output and shifting thematic focuses. Building on an earlier survey, which organized 126 papers collected till November 2023 into eight categories, we present a platform that automates the extraction, categorization, and trend analysis of new papers. Our analysis reports on category drift, identifying evolving perspectives on the use of LLMs for planning. Our analysis reveals a decline in the percentage of papers for six categories, an increase in two, and the emergence of two new categories. Specifically, we contribute by (1) developing an automated system for categorizing new papers into existing or emergent categories, (2) reporting on category shifts with the addition of 47 new papers till September 2024, and (3) introducing a platform for continuous extraction, categorization, and trend tracking in LLM and planning research. This platform also features a leaderboard to encourage innovations in automated paper categorization.

In the digital age, understanding the dynamics of information spread and opinion formation within networks is paramount. This research introduces an innovative framework that combines the principles of opinion dynamics with the strategic capabilities of Automated Planning. We have developed, to the best of our knowledge, the first-ever numeric PDDL tailored for opinion dynamics. Our tool empowers users to visualize intricate networks, simulate the evolution of opinions, and strategically influence that evolution to achieve specific outcomes. By harnessing Automated Planning techniques, our framework offers a nuanced approach to devise sequences of actions tailored to transition a network from its current opinion landscape to a desired state. This holistic approach provides insights into the intricate interplay of individual nodes within a network and paves the way for targeted interventions. Furthermore, the tool facilitates human-AI collaboration, enabling users to not only understand information spread but also devise practical strategies to mitigate potential harmful outcomes arising from it. Demo Video link - https://tinyurl.com/3k7bp99h

Building teams and promoting collaboration are two very common business activities. An example of these are seen in the TeamingForFunding problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel deployed system to recommend teams using a variety of AI methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced amongst the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We validate the success of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams but higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant. Lastly, we evaluate our system in two diverse settings in US and India (of researchers and proposal calls) to establish generality of our approach, and deploy it at a major US university for routine use.

Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems. We aim to keep the categorization of papers updated on https://ai4society.github.io/LLM-Planning-Viz/, a collaborative resource that allows researchers to contribute and add new literature to the categorization.

In this study, we investigate the under-explored intervention planning aimed at disseminating accurate information within dynamic opinion networks by leveraging learning strategies. Intervention planning involves identifying key nodes (search) and exerting control (e.g., disseminating accurate/official information through the nodes) to mitigate the influence of misinformation. However, as the network size increases, the problem becomes computationally intractable. To address this, we first introduce a ranking algorithm to identify key nodes for disseminating accurate information, which facilitates the training of neural network (NN) classifiers that provide generalized solutions for the search and planning problems. Second, we mitigate the complexity of label generation—which becomes challenging as the network grows—by developing a reinforcement learning (RL)-based centralized dynamic planning framework. We analyze these NN-based planners for opinion networks governed by two dynamic propagation models. Each model incorporates both binary and continuous opinion and trust representations. Our experimental results demonstrate that the ranking algorithm-based classifiers provide plans that enhance infection rate control, especially with increased action budgets for small networks. Further, we observe that the reward strategies focusing on key metrics, such as the number of susceptible nodes and infection rates, outperform those prioritizing faster blocking strategies. Additionally, our findings reveal that graph convolutional network (GCN)-based planners facilitate scalable centralized plans that achieve lower infection rates (higher control) across various network configurations (e.g., Watts-Strogatz topology, varying action budgets, varying initial infected nodes, and varying degree of infected nodes).

The state identification problem seeks to identify power usage patterns of any system, like buildings or factories, of interest. In this challenge paper, we make power usage dataset available from 8 institutions in manufacturing, education and medical institutions from the US and India, and an initial unsupervised machine learning based solution as a baseline for the community to accelerate research in this area.

Plansformer is a novel tool that utilizes a fine-tuned language model based on transformer architecture to generate symbolic plans. Transformers are a type of neural network architecture that have been shown to be highly effective in a range of natural language processing tasks. Unlike traditional planning systems that use heuristic-based search strategies, Plansformer is fine-tuned on specific classical planning domains to generate high-quality plans that are both fluent and feasible. Plansformer takes the domain and problem files as input (in PDDL) and outputs a sequence of actions that can be executed to solve the problem. We demonstrate the effectiveness of Plansformer on a variety of benchmark problems and provide both qualitative and quantitative results obtained during our evaluation, including its limitations. Plansformer has the potential to significantly improve the efficiency and effectiveness of planning in various domains, from logistics and scheduling to natural language processing and human-computer interaction. In addition, we provide public access to Plansformer via a website as well as an API endpoint; this enables other researchers to utilize our tool for planning and execution. The demo video is available at https://youtu.be/_1rlctCGsrk

Modern artificial intelligence (AI) methods have been used to solve problems that many humans struggle to solve. This opens up new opportunities for knowledge discovery and education. We demonstrate ALLURE, an educational AI system for learning to solve the Rubik’s cube that is designed to help students improve their problem solving skills. ALLURE can both find and explain its own strategies for solving the Rubik’s cube as well as build on user-provided strategies. Collaboration between AI and user happens using visual and natural language modalities.

Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? In general, how should we account for and balance the ethical values, safety recommendations, and societal norms, when we are trying to achieve a certain objective? To enable effective AI-human collaboration, we must equip AI agents with a model of how humans make such trade-offs in environments where there is not only a goal to be reached, but there are also ethical constraints to be considered and to possibly align with. These ethical constraints could be both deontological rules on actions that should not be performed, or also consequentialist policies that recommend avoiding reaching certain states of the world. Our purpose is to build AI agents that can mimic human behavior in these ethically constrained decision environments, with a long term research goal to use AI to help humans in making better moral judgments and actions. To this end, we propose a computational approach where competing objectives and ethical constraints are orchestrated through a method that leverages a cognitive model of human decision making, called multi-alternative decision field theory (MDFT). Using MDFT, we build an orchestrator, called MDFT-Orchestrator (MDFT-O), that is both general and flexible. We also show experimentally that MDFT-O both generates better decisions than using a heuristic that takes a weighted average of competing policies (WA-O), but also performs better in terms of mimicking human decisions as collected through Amazon Mechanical Turk (AMT). Our methodology is therefore able to faithfully model human decision in ethically constrained decision environments.

Machine translation services are a very popular class of Artificial Intelligence (AI) services nowadays but public's trust in these services is not guaranteed since they have been shown to have issues like bias. In this work, we focus on the behavior of machine translators with respect to gender bias as well as their accuracy. We have created the first-of-its-kind virtual environment, called VEGA, where the user can interactively explore translation services and compare their trust ratings using different visuals.

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research community to define, try and evaluate new methodologies, frameworks, and evaluation metrics, in the spirit of achieving a better understanding of both human and machine intelligence.

Developing the problem solving skills of children is a challenging problem that is crucial for the future of our society. Given that artificial intelligence (AI) has been used to solve problems across a wide variety of domains, AI offers unique opportunities to develop problem solving skills using a multitude of tasks that pique the curiosity of children. To make this a reality, it is necessary to address the uninterpretable “black-box” that AI often appears to be. Towards this goal, we design a collaborative artificial intelligence algorithm that uses a human-in-the-loop approach to allow students to discover their own personalized solutions to problems. This collaborative algorithm builds on state-of-the-art AI algorithms and leverages additional interpretable structures, namely knowledge graphs and decision trees, to create a fully interpretable process that is able to explain solutions in their entirety. We describe this algorithm when applied to solving the Rubik’s cube as well as our planned user-interface and assessment methods.

Competitive analysis is a critical part of any business. Product managers, sellers, and marketers spend time and resources scouring through an immense amount of online and offline content, aiming to discover what their competitors are doing in the marketplace to understand what type of threat they pose to their business' financial well-being. Currently, this process is time and labor-intensive, slow and costly. This paper presents Clarity, a data-driven unsupervised system for assessment of products, which is currently in deployment in the large IT company, IBM. Clarity has been running for more than a year and is used by over 1,500 people to perform over 160 competitive analyses involving over 800 products. The system considers multiple factors from a collection of online content: numeric ratings by online users, sentiments of reviews for key product performance dimensions, content volume, and recency of content. The results and explanations of factors leading to the results are visualized in an interactive dashboard that allows users to track their product's performance as well as understand main contributing factors. Its efficacy has been tested in a series of cases across IBM's portfolio which spans software, hardware, and services.

We demonstrate Water Advisor, a multi-modal assistant to help non-experts make sense of complex water quality data and apply it to their specific needs. A user can chat with the tool about water quality and activities of interest, and the system tries to advise using available water data for a location, applicable water regulations and relevant parameters using AI methods.

We demonstrate an embodied cognitive agent that helps scientists visualize and analyze exo-planets and their host stars. The prototype is situated in a room equipped with a large display, microphones, cameras, speakers, and pointing devices. Users communicate with the agent via speech, gestures, and combinations thereof, and it responds by displaying content and generating synthesized speech. Extensive use of context facilitates natural interaction with the agent.

A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the same expectation needs to be met by automated systems that increasingly get delegated to act on their behalf. A very important aspect of an ethical behavior is to avoid (intended, perceived, or accidental) bias. Bias occurs when the data distribution is not representative enough of the natural phenomenon one wants to model and reason about. The possibly biased behavior of a service is hard to detect and handle if the AI service is merely being used and not developed from scratch, since the training data set is not available. In this situation, we envisage a 3rd party rating agency that is independent of the API producer or consumer and has its own set of biased and unbiased data, with customizable distributions. We propose a 2-step rating approach that generates bias ratings signifying whether the AI service is unbiased compensating, data-sensitive biased, or biased. The approach also works on composite services. We implement it in the context of text translation and report interesting results.

In this demonstration, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human-in-the-loop decision-making. Imposing transparency and explainability requirements on such agents is crucial for establishing human trust and common ground with an end-to-end automated planning system. Visualizing the agent's internal decision making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent: starting from its sensory inputs, to progressively higher order decisions made by it in order to drive its planning components. We demonstrate these functionalities in the context of a smart assistant in the Cognitive Environments Laboratory at IBM's T.J. Watson Research Center.

The emerging paradigm of dialogue interfaces for information retrieval systems opens new opportunities for interactively narrowing down users' information query and improving search results. Prior research has largely focused on methods that use a set of close-ended questions, such as decision tree, to learn about the user's search target. However, when there is a myriad of documents or items to search, solely relying on close-ended questions can lead to long and undesirable dialogues. We propose an adaptive dialogue strategy framework that incorporates open-ended questions at the optimal timing to reduce the length of the dialogue. We propose a method to estimate the information gain of open-ended questions, and in each dialog turn, we compare it with that of close-ended questions to decide which question to ask. We present experiments using several synthetic datasets designed to explore the behavior of such an adaptive dialogue strategy under different environments, and compare the system's performance with that of a close-ended-questions-only strategy.

The complex process of adapting pre-packaged applications, such as Oracle or SAP, to an organization's needs is full of challenges. Although detailed, structured, and well-documented methods govern this process, the consulting team implementing the method must spend a huge amount of manual effort to make sure the guidelines of the method are followed as intended by the method author. MATCON breaks down the method content, documents, templates, and work products into reusable objects, and enables them to be cataloged and indexed so these objects can be easily found and reused on subsequent projects. By using models and meta-modeling the reusable methods, we automatically produce a CASE tool to apply these methods, thereby guiding consultants through this complex process. The resulting tool helps consultants create the method deliverables for the initial phases of large customization projects. Our MATCON output, referred to as Consultant Assistant, has shown significant savings in training costs, a 20 - 30% improvement in productivity, and positive results in large Oracle and SAP implementations.

This write-up provides a summary of the International Workshop on Context enabled Source and Service Selection, Integration and Adaptation (CSSSIA 2008), organized in conjunction with WWW 2008, at Beijing, China on April 22nd 2008. We outline the motivation for organizing the workshop, briefly describe the organizational details and program of the workshop, and summarize each of the papers accepted by the workshop. More information about the workshop can be found at http://www.cs.adelaide.edu.au/~csssia08/.

Web services provide an instantiation of the loosely coupled service–oriented architecture and facilitate the process of enterprise application integration by encapsulating information, software, and other resources. However, to exploit the true potential of web services, it is critical to develop technologies and tools for composing new services from existing ones. While numerous composition approaches have been developed in the past, very little has been done towards tooling. What is clearly lacking is an Integrated Development Environment (IDE) to ease the process of composition, thereby reducing development time and integration efforts. In this paper, we build on our previous work on service composition, and present an IDE for end–to–end composition of web services. We elaborate on the design of the IDE, describe its integration with existing technologies, and discuss its usability based on the findings of a user survey.

Workflows often operate in volatile environments in which the component services' QoS changes frequently. Optimally adapting to these changes becomes an important problem that must be addressed by the Web service composition and execution (WSCE) system being utilized. We adopt the A-WSCE framework that utilizes a three-stage approach for composing and executing Web workflows. The A-WSCE framework offers a way to adapt by defining multiple workflows and switching among them in case of component failure or changes in the QoS parameters. However, the A-WSCE framework suffers from the limitations imposed by a simple strategy of periodically checking the QoS offerings of randomly picked providers in order to decide whether the current workflow is optimal. To address these limitations, we associate the value of changed information (VOC) with each workflow and utilize the VOC to update which workflow to execute. We empirically demonstrate the improved performance of the workflows selected using the new approach in comparison to the original framework.

A variety of processes for managing IT systems are being remotely serviced today. There is a growing realization that in these services, which were hither-to labor-centric, better service quality and reduced cost could be achieved with more automation but it is not clear what steps should be automated and how. We 'present a method, called AutoSeek, to systematically analyze a process to select steps that can be automated in a cost-effective manner with the appropriate level of policy-based automation. In doing so, we balance the savings from automation with the cost of implementating and maintaining the automated steps. AutoSeek has been applied to different types of delivery processes and has been found effective as a broad framework towards systematically making 'process improvements.

In this paper, we present a novel algorithm to compose Web services in the presence of semantic ambiguity by combining semantic matching and AI planning algorithms. Specifically, we use cues from domain-independent and domain-specific ontologies to compute an overall semantic similarity score between ambiguous terms. This semantic similarity score is used by AI planning algorithms to guide the searching process when composing services. Experimental results indicate that planning with semantic matching produces better results than planning or semantic matching alone. The solution is suitable for semi-automated composition tools or directory browsers

Web services simplify enterprise application integration by facilitating reuse of existing components for creating new services. In a dynamic environment, it is imperative to design a Web Service Composition and Execution (WSCE) system that adapts to failure of component services or changes in their QoS offerings. In this paper, we motivate a staged approach for adaptive WSCE (A-WSCE) that cleanly separates the functional and non-functional requirements of a new service, and enables different environmental changes to be absorbed at different stages of composition and execution. We use Synthy, a prototype service creation environment, to implement our solution and demonstrate its effectiveness.

The demand for quickly delivering new applications is increasingly becoming a business imperative today. Application development is often done in an ad hoc manner, without standard frameworks or libraries, thus resulting in poor reuse of software assets. Web services have received much interest in industry due to their potential in facilitating seamless business-to-business or enterprise application integration. A web services composition tool can help automate the process, from creating business process functionality, to developing executable workflows, to deploying them on an execution environment. However, we find that the main approaches taken thus far to standardize and compose web services are piecemeal and insufficient. The business world has adopted a (distributed) programming approach in which web service instances are described using WSDL, composed into flows with a language like BPEL and invoked with the SOAP protocol. Academia has propounded the AI approach of formally representing web service capabilities in ontologies, and reasoning about their composition using goal-oriented inferencing techniques from planning. We present the first integrated work in composing web services end to end from specification to deployment by synergistically combining the strengths of the above approaches. We describe a prototype service creation environment along with a use-case scenario, and demonstrate how it can significantly speed up the time-to-market for new services.

Journals and conference proceedings represent the dominant mechanisms of reporting new biomedical results. The unstructured nature of such publications makes it difficult to utilize data mining or automated knowledge discovery techniques. Annotation (or markup) of these unstructured documents represents the first step in making these documents machine analyzable. In this paper we first present a system called BioAnnotator for identifying and annotating biological terms in documents. BioAnnotator uses domain based dictionary look-up for recognizing known terms and a rule engine for discovering new terms. The combination and dictionary look-up and rules result in good performance (87% precision and 94% recall on the GENIA 1.1 corpus for extracting general biological terms based on an approximate matching criterion). To demonstrate the subsequent mining and knowledge discovery activities that are made feasible by BioAnnotator, we also present a system called MedSummarizer that uses the extracted terms to identify the common concepts in a given group of genes.

The emerging biochip technology has made it possible to simultaneously study expression (activity level) of thousands of genes or proteins in a single experiment in the laboratory. However, in order to extract relevant biological knowledge from the biochip experimental data, it is critical not only to analyze the experimental data, but also to cross-reference and correlate these large volumes of data with information available in external biological databases accessible online. We address this problem in a comprehensive system for knowledge management in bioinformatics called e2e. To the biologist or biological applications, e2e exposes a common semantic view of inter-relationship among biological concepts in the form of an XML representation called eXpressML, while internally, it can use any data integration solution to retrieve data and return results corresponding to the semantic view. We have implemented an e2e prototype that enables a biologist to analyze her gene expression data in GEML or from a public site like Stanford, and discover knowledge through operations like querying on relevant annotated data represented in eXpressML using pathways data from KEGG, publication data from Medline and protein data from SWISS-PROT.

Existing plan synthesis approaches in artificial intelligence fall into two categories -- domain independent and domain dependent. The domain independent approaches are applicable across a variety of domains, but may not be very efficient in any one given domain. The domain dependent approaches need to be (re)designed for each domain separately, but can be very efficient in the domain for which they are designed. One enticing alternative to these approaches is to automatically synthesize domain independent planners given the knowledge about the domain and the theory of planning. In this paper, we investigate the feasibility of using existing automated software synthesis tools to support such synthesis. Specifically, we describe an architecture called CLAY in which the Kestrel Interactive Development System (KIDS) is used to derive a domain-customized planner through a semi-automatic combination of a declarative theory of planning, and the declarative control knowledge specific to a given domain, to semi-automatically combine them to derive domain-customized planners. We discuss what it means to write a declarative theory of planning and control knowledge for KIDS, and illustrate our approach by generating a class of domain-specific planners using state space refinements. Our experiments show that the synthesized planners can outperform classical refinement planners (implemented as instantiations of UCP, Kambhampati & Srivastava, 1995), using the same control knowledge. We will contrast the costs and benefits of the synthesis approach with conventional methods for customizing domain independent planners.

Plan synthesis approaches in AI fall into two categories: domain-independent and domain-dependent. The domain-independent approaches are applicable across a variety of domains, but may not be very efficient in any one given domain. The domain-dependent approaches can be very efficient for the domain for which they are designed, but would need to be written separately for each domain of interest. The tediousness and the error-proneness of manual coding have hither-to inhibited work on domain-dependent planners. In this paper we describe a novel way of automating the development of domain dependent planners using knowledge-based software synthesis tools. Specifically, we describe an architecture called CLAY in which the Kestrel Interactive Development System (KIDS) is used in conjunction with a declarative theory of domain independent planning, and the declarative control knowledge specific to a given domain, to semi-automatically derive customized planning code. We discuss what it means to write declarative theory of planning and control knowledge for KIDS, and illustrate it by generating a range of domain-specific planners using state space and plan space refinements. We demonstrate that the synthesized planners can have superior performance compared to classical refinement planners using the same control knowledge.