50 citations
- Accenture (United States)US3 papers
- University College LondonGB2 papers
- American UniversityUS1 paper
- Astana Medical UniversityKZ1 paper
- California Institute of Integral StudiesUS1 paper
- École des hautes études en sciences socialesFR1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Georgia Institute of TechnologyUS1 paper
- GoodAI (Czechia)CZ1 paper
- Independent University of MoscowRU1 paper
- Indian Institute of Technology IndoreIN1 paper
- Indian Institute of Technology PatnaIN1 paper
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
Genliang Zhu, Chu Wang
Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection. We present Explanation-Bou…
cs.SE2026★ 1 cited
SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment
Priyavanshi Pathania, Rohit Mehra, Vibhu Saujanya Sharma +4
Large Language Models are rapidly gaining traction in software engineering, yet their growing carbon footprint raises pressing sustainability concerns. While training emissions are…