state-grounding

Tag

Cards List
#state-grounding

SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents

arXiv cs.AI · yesterday Cached

SAGE is a novel evaluation framework for task-oriented dialogue agents that grounds assessments in dialogue state changes and uses abstention to provide cost-effective, accurate turn-level judgments without expensive LLM calls.

0 favorites 0 likes
#state-grounding

@_akhaliq: StateAct Program State, before Pixels, for Long-Horizon Computer-Use Agents paper: https://huggingface.co/papers/2607.2…

X AI KOLs Timeline · 2026-07-28 Cached

StateAct proposes a code-first, multi-agent system for long-horizon computer-use agents that operates directly on program state instead of screenshots, achieving higher success rates and lower costs on OSWorld2.0.

0 favorites 0 likes
← Back to home

Submit Feedback