An official website of the United States government
Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.
more »
« less
Re-examining the Planning Basis of Goal-driven Autonomy Problems
The study of goal-reasoning agents capable of integrated action and execution has received a great deal of attention in recent years. While practical implementations and theoretical insights of such agents have provided a wealth of flexible behavior in a variety of task environments, they tend to focus on complex environments that are far from classical planning assumptions. This paper formalizes classical planning problems where an agent can change its goal(s) during execution. We identify the minimal changes to classical planning and formalize a model that supports "classical goal reasoning."
more »
« less
- Award ID(s):
- 2046294
- PAR ID:
- 10337384
- Date Published:
- Journal Name:
- Proceedings of the Workshop on Integrated Action and Execution at the 32nd International Conference on Automated Planning and Scheduling
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cox, Michael T. (Ed.)Goal reasoning agents can solve novel problems by detecting an anomaly between expectations and observations; generating explanations about plausible causes for the anomaly; and formulating goals to remove the cause. Yet not all anomalies represent problems. We claim that the task of discerning the difference between benign anomalies and those that represent an actual problem by an agent will increase its performance. Furthermore, we present a new definition of the term “problem” in a goal reasoning context. This paper discusses the role of explanations and goal formulation in response to developing problems and implements the response. The paper illustrates goal formulation in a mine clearance domain and a labor relations domain. We also show the empirical difference between a standard planning agent, an agent that detects anomalies and an agent that recognizes problems.more » « less
-
Goal reasoning agents can solve novel problems by detecting an anomaly between expectations and observations, generating explanations about plausible causes for the anomaly, and formulating goals to remove the cause. Yet, not all anomalies represent problems. This paper addresses discerning the difference between benign anomalies and those that represent an actual problem for an agent. Furthermore, we present a new definition of the term “problem” in a goal reasoning context. This paper discusses the role of explanations and goal formulation in response to the developing problems and implements it; the paper also illustrates the above in a mine clearance domain and a labor relations domain. We also show the empirical difference between a standard planning agent, an agent that detects anomalies, and an agent that recognizes problems.more » « less
-
null (Ed.)Abstract Designing agents that reason and act upon the world has always been one of the main objectives of the Artificial Intelligence community. While for planning in “simple” domains the agents can solely rely on facts about the world, in several contexts, e.g. , economy, security, justice and politics, the mere knowledge of the world could be insufficient to reach a desired goal. In these scenarios, epistemic reasoning, i.e. , reasoning about agents’ beliefs about themselves and about other agents’ beliefs, is essential to design winning strategies. This paper addresses the problem of reasoning in multi-agent epistemic settings exploiting declarative programming techniques. In particular, the paper presents an actual implementation of a multi-shot Answer Set Programming -based planner that can reason in multi-agent epistemic settings, called PLATO (e P istemic mu L ti-agent A nswer se T programming s O lver). The ASP paradigm enables a concise and elegant design of the planner, w.r.t. other imperative implementations, facilitating the development of formal verification of correctness. The paper shows how the planner, exploiting an ad-hoc epistemic state representation and the efficiency of ASP solvers, has competitive performance results on benchmarks collected from the literature.more » « less
-
Robot manipulation in cluttered environments of-ten requires complex and sequential rearrangement of multiple objects in order to achieve the desired reconfiguration of the target objects. Due to the sophisticated physical interactions involved in such scenarios, rearrangement-based manipulation is still limited to a small range of tasks and is especially vulnerable to physical uncertainties and perception noise. This paper presents a planning framework that leverages the efficiency of sampling-based planning approaches, and closes the manipulation loop by dynamically controlling the planning horizon. Our approach interleaves planning and execution to progressively approach the manipulation goal while correcting any errors or path deviations along the process. Meanwhile, our framework allows the definition of manipulation goals without requiring explicit goal configurations, enabling the robot to flexibly interact with all objects to facilitate the manipulation of the target ones. With extensive experiments both in simulation and on a real robot, we evaluate our framework on three manipulation tasks in cluttered environments: grasping, relocating, and sorting. In comparison with two baseline approaches, we show that our framework can significantly improve planning efficiency, robustness against physical uncertainties, and task success rate under limited time budgets.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
