Related papers: From Theory to Protocol: Executable Frameworks for…
Thinking aloud is an effective meta-cognitive strategy human reasoners apply to solve difficult problems. We suggest to improve the reasoning ability of pre-trained neural language models in a similar way, namely by expanding a task's…
Informal arguments that cryptographic protocols are secure can be made rigorous using inductive definitions. The approach is based on ordinary predicate calculus and copes with infinite-state systems. Proofs are generated using…
The foundation of reproducible science lies in protocols that are precise, logically ordered, and executable. The autonomous generation of these protocols through natural language queries could greatly improve the efficiency of the…
We show that interactive protocols between a prover and a verifier, a well-known tool of complexity theory, can be used in practice to certify the correctness of automated reasoning tools. Theoretically, interactive protocols exist for all…
The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…
The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study agents that compose pre-trained policies as temporally extended actions, enabling solutions to…
Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We propose G2CP…
The progression from traditional prompt engineering to a more rigorous discipline of prompt design marks a pivotal shift in human-LLM interaction. As Large Language Models (LLMs) become increasingly embedded in mission-critical…
Edges, binding together nodes within networks, have the potential to induce dramatic transitions when specific collective failure behaviors emerge. These changes, initially unfolding covertly and then erupting abruptly, pose substantial,…
Current text-to-3D methods excel at generating single objects but falter on compositional prompts. We argue this failure is fundamental to their optimization schedules, as simultaneous or iterative heuristics predictably collapse under a…
Compositionality in knowledge and language--the ability to represent complex concepts as a combination of simpler ones--is a hallmark of human cognition and communication. Despite recent advances, deep neural networks still struggle to…
Determining if two protocols can be securely composed requires analyzing not only their additive properties but also their destructive properties. In this paper we propose a new composition method for constructing protocols based on…
This work addresses the design of multi-agent coordination through high-order consensus protocols. While first-order consensus strategies are well-studied -- with known robustness to uncertainties such as time delays, time-varying weights,…
Humans have a remarkable ability to make decisions by accurately reasoning about future events, including the future behaviors and states of mind of other agents. Consider driving a car through a busy intersection: it is necessary to reason…
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning. Our robot interacts with objects using an initial action…
An observational study was conducted on a professional designer working on a design project in aerospace industry. The protocol data were analyzed in order to gain insight into the actions the designer used for the development of a solution…
Global protocol specifications are the starting point of top-down verification methodologies, and serve as a blueprint for synthesizing local specifications that guarantee the correctness of distributed implementations. In this work, we…
This paper establishes a fundamental convergence: Schema-Guided Dialogue (SGD) and the Model Context Protocol (MCP) represent two manifestations of a unified paradigm for deterministic, auditable LLM-agent interaction. SGD, designed for…
Existing approaches to coalition formation often assume that requirements associated with tasks are precisely specified by the human operator. However, prior work has demonstrated that humans, while extremely adept at solving complex…
We study the round and communication complexities of various cryptographic protocols. We give tight lower bounds on the round and communication complexities of any fully black-box reduction of a statistically hiding commitment scheme from…