Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection

arXiv:2608.05085 · cs.LG, cs.AI · Submitted 2026-08-05 · Read on arXiv

Ahmed Hassoon, Mark Dredze

cs.LG, cs.AI

Submitted: 2026-08-05

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Planner — 34× in this paper · explained in 3 episodes
• Information Gain — 11× in this paper · explained in 2 episodes
• Abstraction — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Admissibility — 6× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Performance Gap — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 3 episodes
• Hypergraph — 2× in this paper · explained in 2 episodes
• Monotonicity — 2× in this paper · explained in 2 episodes
• POMDP — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 6 episodes
• Agentic AI — 1× in this paper · explained in 2 episodes
• Bayesian Optimization — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Causal Discovery — 1× in this paper · explained in 3 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Editor — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Expected Information Gain (EIG) — 1× in this paper · explained in 3 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Harness — 1× in this paper · explained in 2 episodes
• Hypergraphs — 1× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 1× in this paper
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reward Function — 1× in this paper · explained in 4 episodes
• Task Planning — 1× in this paper · explained in 2 episodes
• Temporal Abstraction — 1× in this paper · explained in 2 episodes

Sources

• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• Kosmos: An AI Scientist for Autonomous Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks