Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/nomeata/loogle
Project page: https://teorth.github.io/pfr
Sources
- Aristotle: IMO-level Automated Theorem Proving
- Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
- QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
- ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
- The Equational Theories Project: Advancing Collaborative Mathematical Research at Scale
- ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization
- Baldur: Whole-Proof Generation and Repair with Large Language Models
- A Semantic Search Engine for Mathlib4
- Automatic Textbook Formalization
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- Automated Conjecture Resolution with Formal Verification
- Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
- LeanAgent: Lifelong Learning for Formal Theorem Proving
- Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
- Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
- ASSESS: A Semantic and Structural Evaluation Framework for Statement Similarity
- Generalized Tree Edit Distance (GTED): A Faithful Evaluation Metric for Statement Autoformalization
- FormalAlign: Automated Alignment Evaluation for Autoformalization
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