Schema: Discovering Unknown Environments via Agentic Program Induction
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Project page: https://schema-harness.github.io/Abstract
Sources
- Synthesizing world models for bilevel planning
- Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
- ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
- Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
- DiG-bench: Discovery in Games
- OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Competitive Programming with Large Reasoning Models
- PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
- NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
- BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
- One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
- Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- MemGPT: Towards LLMs as Operating Systems
- TextQuests: How Good are LLMs at Text-Based Video Games?
- Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
- PoE-World: Compositional World Modeling with Products of Programmatic Experts
- Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems