Related papers: Computability of Agentic Systems
In this paper, we focus on task-specific question answering (QA). To this end, we introduce a method for generating exhaustive and high-quality training data, which allows us to train compact (e.g., run on a mobile device), task-specific QA…
Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such…
Agentic tasks, which require multi-step problem solving with autonomy, tool use, and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. However, existing instruction data lacks tool interaction, and…
To scrutinize notions of computation and time complexity, we introduce and formally define an interactive model for computation that we call it the \emph{computation environment}. A computation environment consists of two main parts: i) a…
Artifact systems are a novel paradigm for specifying and implementing business processes described in terms of interacting modules called artifacts. Artifacts consist of data and lifecycles, accounting respectively for the relational…
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the…
This work introduces an end-to-end graph-based agent for accelerating the computational efficiency of Benders Decomposition. The agent's policy is parameterized by a graph neural network which takes as input a bipartite graph representation…
Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…
We establish a correspondence between equivalence classes of agent-state policies for deterministic POMDPs and one-input process functions (the classical-deterministic limit of higher-order quantum operations). We use this correspondence to…
OpenAI's ChatGPT Atlas introduces new capabilities for web interaction, enabling the model to analyze webpages, process user intents, and execute cursor and keyboard inputs directly within the browser. While its capacity for information…
We witness an unprecedented proliferation of knowledge graphs that record millions of entities and their relationships. While knowledge graphs are structure-flexible and content rich, they are difficult to use. The challenge lies in the gap…
Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG…
With the development of deep learning technology, large language models have achieved remarkable results in many natural language processing tasks. However, these models still have certain limitations in handling complex reasoning tasks and…
Underlying relationships among multi-agent systems (MAS) in hazardous scenarios can be represented as Game-theoretic models. We measure the performance of MAS achieving tasks from the perspective of balancing success probability and system…
From software development to robot control, modern agentic systems decompose complex objectives into a sequence of subtasks and choose a set of specialized AI agents to complete them. We formalize agentic workflows as directed acyclic…
Training trustworthy agentic LLMs requires data that shows the grounded reasoning process, not just the final answer. Existing datasets fall short: question-answering data is outcome-only, chain-of-thought data is not tied to specific…
In this paper, a computationally efficient data-driven hybrid automaton model is proposed to capture unknown complex dynamical system behaviors using multiple neural networks. The sampled data of the system is divided by valid partitions…
An Automata Network is a map ${f:Q^n\rightarrow Q^n}$ where $Q$ is a finite alphabet. It can be viewed as a network of $n$ entities, each holding a state from $Q$, and evolving according to a deterministic synchronous update rule in such a…
We consider the category of partially observable dynamical systems, to which the entropy theory of dynamical systems extends functorially. This leads us to introduce quotient-topological entropy. We discuss the structure that emerges. We…
In implementing evaluation strategies of the lambda-calculus, both correctness and efficiency of implementation are valid concerns. While the notion of correctness is determined by the evaluation strategy, regarding efficiency there is a…