Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

daVinci-Prover: Agent-Native Mid-Training for Formal Theorem Proving

Wenhong Zhu, Xuefeng Li, Jiashuo Zhang, Yu Chen +3 more

Published

Nov 12, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

15% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 12, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Long Horizon

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Advances in large language models (LLMs) are rapidly transforming formal theorem proving. Yet further progress remains constrained by the lack of a transparent and effective data recipe for systematically improving theorem-proving models. In this work, we argue that effective agentic provers require strong mathematical skill priors to ground theorem proving and agentic trajectories to enable long-horizon, interactive proof construction. To this end, we synthesize an agent-native 33.7B-token mid-training corpus covering decomposition, search, self-verification, and revision, together with verifier-grounded agentic trajectories. We further introduce the daVinci-Prover harness, which enables models to construct proofs and interact with a Lean verifier in an isolated workspace, and use it to collect approximately 36K high-quality agent trajectories for supervised fine-tuning. Our mid-training recipe yields an average improvement of 13.7 points over the matched Qwen3-8B SFT-only baseline across MiniF2F, FATE-M, and ProofNet. When applied to the Qwen3.5 series, our approach also yields strong performance across theorem-proving benchmarks and achieves near-saturating MiniF2F performance with memory compaction. The results highlight agent-native mid-training as an effective foundation for developing stronger interactive theorem-proving agents.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Advances in large language models (LLMs) are rapidly transforming formal theorem proving."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Advances in large language models (LLMs) are rapidly transforming formal theorem proving."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Advances in large language models (LLMs) are rapidly transforming formal theorem proving."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Advances in large language models (LLMs) are rapidly transforming formal theorem proving."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Advances in large language models (LLMs) are rapidly transforming formal theorem proving."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Trajectory (inferred)
Expertise required
Math
Evaluation details
Evaluation modes
None
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Advances in large language models (LLMs) are rapidly transforming formal theorem proving.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Advances in large language models (LLMs) are rapidly transforming formal theorem proving.
  • Yet further progress remains constrained by the lack of a transparent and effective data recipe for systematically improving theorem-proving models.
  • In this work, we argue that effective agentic provers require strong mathematical skill priors to ground theorem proving and agentic trajectories to enable long-horizon, interactive proof construction.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Long-horizon tasks) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Advances in large language models (LLMs) are rapidly transforming formal theorem proving.
  • Yet further progress remains constrained by the lack of a transparent and effective data recipe for systematically improving theorem-proving models.

Why it matters for eval

  • When applied to the Qwen3.5 series, our approach also yields strong performance across theorem-proving benchmarks and achieves near-saturating MiniF2F performance with memory compaction.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.