Agentick is a new benchmark for sequential decision-making agents that evaluates RL, LLM, VLM, hybrid, and human approaches across 37 tasks and finds no single method dominates.
Maestromotif: Skill design from artificial intelligence feedback.arXiv preprint arXiv:2412.08542
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Hierarchical Behaviour Spaces uses linear combinations of reward functions to induce expressive behavior spaces in hierarchical RL, yielding strong performance on NetHack primarily through better exploration rather than long-term planning.
citing papers explorer
-
Agentick: A Unified Benchmark for General Sequential Decision-Making Agents
Agentick is a new benchmark for sequential decision-making agents that evaluates RL, LLM, VLM, hybrid, and human approaches across 37 tasks and finds no single method dominates.
-
Hierarchical Behaviour Spaces
Hierarchical Behaviour Spaces uses linear combinations of reward functions to induce expressive behavior spaces in hierarchical RL, yielding strong performance on NetHack primarily through better exploration rather than long-term planning.