Copertina

Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Armesto, Maximiliano, Kolb, Christophe
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs
di: Armesto, Maximiliano, et al.
Pubblicazione: (2026)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
di: Wei, Jinbiao, et al.
Pubblicazione: (2026)

AgentSLA : Towards a Service Level Agreement for AI Agents
di: Jouneaux, Gwendal, et al.
Pubblicazione: (2025)

Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding
di: Armesto, Maximiliano, et al.
Pubblicazione: (2026)

Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications
di: Wang, Yongchao, et al.
Pubblicazione: (2026)

On the Adoption of AI Coding Agents in Open-source Android and iOS Development
di: Khan, Muhammad Ahmad, et al.
Pubblicazione: (2026)

Semantic Caching and Intent-Driven Context Optimization for Multi-Agent Natural Language to Code Systems
di: Singh, Harmohit
Pubblicazione: (2026)

Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents
di: Dang, Hy, et al.
Pubblicazione: (2026)

Quantifying the Expectation-Realisation Gap for Agentic AI Systems
di: Lobentanzer, Sebastian
Pubblicazione: (2026)

OpenHands: An Open Platform for AI Software Developers as Generalist Agents
di: Wang, Xingyao, et al.
Pubblicazione: (2024)

Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents
di: Lu, Qinghua, et al.
Pubblicazione: (2023)

The Unreasonable Effectiveness of Open Science in AI: A Replication Study
di: Gundersen, Odd Erik, et al.
Pubblicazione: (2024)

The AI Agent Index
di: Casper, Stephen, et al.
Pubblicazione: (2025)

AgentGuard: Runtime Verification of AI Agents
di: Koohestani, Roham
Pubblicazione: (2025)

Towards a Framework for Openness in Foundation Models: Proceedings from the Columbia Convening on Openness in Artificial Intelligence
di: Basdevant, Adrien, et al.
Pubblicazione: (2024)

TAI3: Testing Agent Integrity in Interpreting User Intent
di: Feng, Shiwei, et al.
Pubblicazione: (2025)

SpecRover: Code Intent Extraction via LLMs
di: Ruan, Haifeng, et al.
Pubblicazione: (2024)

Embedding Software Intent: Lightweight Java Module Recovery
di: He, Yirui, et al.
Pubblicazione: (2025)

From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
di: De La Cruz, Elyson
Pubblicazione: (2026)

Towards a Science of Causal Interpretability in Deep Learning for Software Engineering
di: Palacio, David N.
Pubblicazione: (2025)

The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
di: Wang, Xingyao, et al.
Pubblicazione: (2025)

Towards Adaptive Software Agents for Debugging
di: Majdoub, Yacine, et al.
Pubblicazione: (2025)

An Empirical Study of Agent Developer Practices in AI Agent Frameworks
di: Wang, Yanlin, et al.
Pubblicazione: (2025)

AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents
di: Pautsch, Erik, et al.
Pubblicazione: (2025)

From Context to Intent: Reasoning-Guided Function-Level Code Completion
di: Li, Yanzhou, et al.
Pubblicazione: (2025)

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
di: Son, Ha Min, et al.
Pubblicazione: (2025)

CIRCLE: A Framework for Evaluating AI from a Real-World Lens
di: Schwartz, Reva, et al.
Pubblicazione: (2026)

Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source
di: Rahman, Musfiqur, et al.
Pubblicazione: (2026)

An Empirical Study of OpenAI API Discussions on Stack Overflow
di: Chen, Xiang, et al.
Pubblicazione: (2025)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
di: Zhang, Zehua, et al.
Pubblicazione: (2025)

GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing
di: Chen, Xiaoyi, et al.
Pubblicazione: (2026)

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion
di: Jiang, Tianyue, et al.
Pubblicazione: (2026)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
di: Liang, Jiarong, et al.
Pubblicazione: (2026)

Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation
di: Lyu, Zongyi, et al.
Pubblicazione: (2025)

OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software
di: Meng, Lingkai, et al.
Pubblicazione: (2025)

Toward a Cohesive AI and Simulation Software Ecosystem for Scientific Innovation
di: Heroux, Michael A., et al.
Pubblicazione: (2024)

AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents
di: Vangala, Bhanu Prakash, et al.
Pubblicazione: (2025)

PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
di: Narayanan, Athma, et al.
Pubblicazione: (2025)

AIDev: Studying AI Coding Agents on GitHub
di: Li, Hao, et al.
Pubblicazione: (2026)

Skilled AI Agents for Embedded and IoT Systems Development
di: Li, Yiming, et al.
Pubblicazione: (2026)