2 papers
cs.RO2026
SAGE: Symbolic Action-Gating and Editing for LLM Task Planners
Trung Minh Bui, JongSul Moon, YoungOuk Kim +3
Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a grounded model of the environment…
cs.SE2026
CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation
Duy Tung Doan, Quang Huy Phung, Dzung Nguyen +1
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated executio…