Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
hub
Open-ended learning leads to generally capable agents
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
polarities
background 2representative citing papers
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
Multitask Preplay replays experience from pursued tasks as starting points for counterfactual simulation of unpursued tasks to learn predictive representations that support fast generalization in humans and machines.
HExA is a training-free agent framework that improves LLM performance on novel physics tasks from 2% to 77% by iteratively designing experiments and composing learned skills.
Task diversity along map, object, and hierarchy axes produces local transfer across shifts in a new continual RL benchmark but fails to sustain learning as the number of shifts grows.
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
GITM uses LLMs to generate action plans from text knowledge and memory, enabling agents to complete long-horizon Minecraft tasks at much higher success rates than prior RL methods.
The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.
Open-ended intelligence is formalized as the compositional closure L(P,C) of primitives P under operators C, with next primitive prediction proposed as an objective to acquire reusable primitives and grammar for lifelong adaptation.
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.
citing papers explorer
-
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.