# Isabelle/HOL proof assistant

Isabelle is a generic proof assistant for expressing mathematical formulas in a formal language and proving them in a logical calculus.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving

DevFeed: [Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving](<https://devfeed.tech/articles/isabelle-pool-server-a-pooled-verification-service-for-prover-training-and-multi-agent-proving-142832.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24788>)

Author: Xuanwei Ren, Wenda Li

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Isabelle/HOL proof assistant](<https://devfeed.tech/topics/isabelle-hol-proof-assistant.md>), [Formal verification](<https://devfeed.tech/topics/formal-verification.md>)

Tags: [admission](<https://devfeed.tech/tags/admission.md>), [api](<https://devfeed.tech/tags/api.md>), [block](<https://devfeed.tech/tags/block.md>), [budget](<https://devfeed.tech/tags/budget.md>), [build](<https://devfeed.tech/tags/build.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [container](<https://devfeed.tech/tags/container.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [headless](<https://devfeed.tech/tags/headless.md>), [http](<https://devfeed.tech/tags/http.md>), [interface](<https://devfeed.tech/tags/interface.md>), [isabelle](<https://devfeed.tech/tags/isabelle.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [memory-pressure](<https://devfeed.tech/tags/memory-pressure.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [python](<https://devfeed.tech/tags/python.md>), [server](<https://devfeed.tech/tags/server.md>), [service](<https://devfeed.tech/tags/service.md>), [training](<https://devfeed.tech/tags/training.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Isabelle Pool Server (IPS) serves warm, headless Isabelle sessions through an HTTP API, with session leasing and reclamation, memory-aware admission control, and per-call time limits. Its interface supports single-step execution, block-level checking, whole-theory builds, and checkpoints for branching and backtracking; a fresh build is the final arbiter. It is available as a container through a Python client, two MCP servers, or raw HTTP. In the reported measurements, IPS matched PIDE MCP at one worker and outperformed it at eight (at an October 2026 commit); with sessions running, it handled 32 concurrent workers on one host at 24 times the single-worker rate. Under memory pressure, it rejects new sessions to preserve existing ones.

### Source excerpt

arXiv:2611.24788v1 Announce Type: cross Abstract: Isabelle Pool Server (IPS), a verification service with a pool of warm headless Isabelle sessions behind an HTTP API, with session leasing and reclamation, memory-aware admission control, and a time budget on every call. Its verification interface spans single-step execution, block-level proof checking and whole-theory builds, with checkpoints for cheap branching and backtracking, and a build from scratch as the final arbiter. The service runs as a single container with monitoring and is accessible via a Python client, two MCP servers and a raw HTTP API. In our measurements IPS is level with PIDE MCP, a PIDE frontend for agents, at one worker and ahead of it at eight, at its commit of October 2026 (the tool is now PIDE AI). Once its sessions are up it scales to 32 concurrent workers on one host at 24 times the single-worker rate, and under memory pressure it refuses new sessions rather than losing existing ones. IPS is free software and publicly available at https://github.com/Deep-LCF/Isabelle-Pool-Server

## Python Code Generation for Isabelle/HOL

DevFeed: [Python Code Generation for Isabelle/HOL](<https://devfeed.tech/articles/python-code-generation-for-isabelle-hol-139611.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22613>)

Author: Nikolaus Huber, Roly Perera, Dominic Orchard

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Isabelle/HOL proof assistant](<https://devfeed.tech/topics/isabelle-hol-proof-assistant.md>), [Python](<https://devfeed.tech/topics/python.md>), [Compilers and Linkers](<https://devfeed.tech/topics/compilers-and-linkers.md>), [Functional programming](<https://devfeed.tech/topics/functional-programming.md>), [Haskell](<https://devfeed.tech/topics/haskell.md>), [OCaml](<https://devfeed.tech/topics/ocaml.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-structures-and-algorithms](<https://devfeed.tech/tags/data-structures-and-algorithms.md>), [isabelle](<https://devfeed.tech/tags/isabelle.md>), [python](<https://devfeed.tech/tags/python.md>)

### AI overview

The work adds a Python backend to Isabelle/HOL's code generator, allowing functions in Isabelle's executable logic to be generated for use in Python applications. It also enables verified implementations to act as references for differential testing of established Python libraries. The authors report validation with regression suites covering large parts of the HOL library and tests of six verified data structures and algorithms against existing Python libraries. Generated code is slower than hand-written libraries, so the abstract presents it as particularly suitable for a verified reference.

### Source excerpt

arXiv:2611.22613v1 Announce Type: cross Abstract: The Isabelle theorem prover provides an environment for formalising mathematics and reasoning about programs. To make verified implementations practically usable, its code generator translates functions expressed in the executable fragment of its logic into conventional programming languages. Its targets have traditionally been functional languages (Standard ML, OCaml, Haskell, and Scala), recently joined by Go. Python, which is becoming the dominant language of scientific computing, data science, and education, has remained out of reach. In this work, we close this gap with a Python backend for Isabelle's code generator. This generator enables verified algorithms to be used in Python applications, or to serve as verified references against which established Python libraries can be differentially tested, without leaving the Python ecosystem. We validate the backend on regression suites covering large parts of the HOL library and by testing six verified data structures and algorithms against established Python libraries. The generated code is slower than hand-written libraries, but well suited as a verified reference.

## Theorem-Proving Agent over Abstract Syntax Tree

DevFeed: [Theorem-Proving Agent over Abstract Syntax Tree](<https://devfeed.tech/articles/theorem-proving-agent-over-abstract-syntax-tree-131673.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.16372>)

Author: Qiyuan Xu, Joshua Ong Jun Leang, Renxi Wang, Wenda Li, Haonan Li, Luke Ong, Conrad Watt

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Isabelle/HOL proof assistant](<https://devfeed.tech/topics/isabelle-hol-proof-assistant.md>), [Formal verification](<https://devfeed.tech/topics/formal-verification.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Concrete syntax tree](<https://devfeed.tech/topics/cst.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ast](<https://devfeed.tech/tags/ast.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [isabelle](<https://devfeed.tech/tags/isabelle.md>), [json](<https://devfeed.tech/tags/json.md>), [llm](<https://devfeed.tech/tags/llm.md>), [proofs](<https://devfeed.tech/tags/proofs.md>), [syntax](<https://devfeed.tech/tags/syntax.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Agent over AST (AoA) represents Minilang proofs as JSON abstract syntax trees and edits a unified proof tree in which each operation carries its subgoal state. This avoids emitting concrete source text and separately locating proof states by line number, which the abstract identifies as a source of repeated work and cost. Against Amazon's Isabelle Agent on the benchmarks' common success sets, AoA reportedly used 2.9-6.9x fewer tokens and 3.9-8.9x fewer tool calls, finished 1.4-2.0x faster, and reduced API cost 2.3-4.7x under normalized input-cache accounting. The abstract also reports substantially more solved problems on the harder verification benchmark; it does not provide the counts here.

### Source excerpt

arXiv:2607.16372v2 Announce Type: replace Abstract: Interactive theorem proving (ITP) underpins program verification and formalized mathematics, but its manual effort limits scalability. LLM-based proof agents promise to ease this effort, but their heavy token consumption and API cost remain a major obstacle. We trace this cost to a shared root: current agents operate on serialized concrete syntax, emitting proofs as source text and recovering proof states through separate, line-number-based queries, so every edit shifts later lines and forces repeated relocation of errors and states. This same dependence on concrete syntax also blocks adoption of Minilang, a recent proof language that reaches SOTA on LLM-based proving but is too new for LLMs' training corpora. We address both problems by lifting the agent off source text and onto the abstract syntax tree (AST): the model supplies proofs as JSON representations of Minilang's AST -- native to tool-calling LLMs -- and drives the prover through a tree-edit model that fuses proof operations and states into one proof tree, so each operation carries its own subgoal's state, readable directly off the tree. We realize this design in \emph{Agent over AST} (AoA). Against Amazon's Isabelle Agent on miniF2F and NTP4VC-Pearl common success sets, AoA cuts API cost by 2.3--4.7x (normalized input-cache accounting), uses 2.9--6.9x fewer tokens and 3.9--8.9x fewer tool calls, and finishes 1.4--2.0x faster -- while also solving far more problems on the harder verification benchmark.

## ProofStudio: Five Proof Assistants in the Browser

DevFeed: [ProofStudio: Five Proof Assistants in the Browser](<https://devfeed.tech/articles/proofstudio-five-proof-assistants-in-the-browser-118052.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05540>)

Author: Yutaka Nagashima

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Isabelle/HOL proof assistant](<https://devfeed.tech/topics/isabelle-hol-proof-assistant.md>), [Formal verification](<https://devfeed.tech/topics/formal-verification.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Lean](<https://devfeed.tech/topics/lean.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistance](<https://devfeed.tech/tags/ai-assistance.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [automation](<https://devfeed.tech/tags/automation.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [education](<https://devfeed.tech/tags/education.md>), [examples](<https://devfeed.tech/tags/examples.md>), [explore](<https://devfeed.tech/tags/explore.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [formal](<https://devfeed.tech/tags/formal.md>), [hol](<https://devfeed.tech/tags/hol.md>), [installation](<https://devfeed.tech/tags/installation.md>), [interface](<https://devfeed.tech/tags/interface.md>), [lean](<https://devfeed.tech/tags/lean.md>), [light](<https://devfeed.tech/tags/light.md>), [local](<https://devfeed.tech/tags/local.md>), [proofs](<https://devfeed.tech/tags/proofs.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [software-verification](<https://devfeed.tech/tags/software-verification.md>)

### AI overview

ProofStudio offers browser access to Isabelle/HOL, Lean, Rocq, HOL4, and HOL Light without local installation. It combines worked examples, preconfigured proof search, and contextual AI assistance in one interface, while showing each prover's native feedback. The stated aim is to reduce installation and learning barriers and help users explore formal specifications and proofs. The abstract also emphasizes that automation does not remove the need to judge whether a formal statement captures the intended requirements.

### Source excerpt

arXiv:2611.05540v1 Announce Type: new Abstract: Recent advances in AI-assisted proof automation are extending the use of proof assistants in software verification and mathematics. However, greater proof automation does not remove users' responsibility to assess whether formal statements capture their intended requirements, making education in formal specification and reasoning essential. To lower the installation and learning barriers associated with mature proof assistants, we present ProofStudio, a browser-based environment integrating Isabelle/HOL, Lean, Rocq, HOL4, and HOL Light with corresponding worked examples, preconfigured proof search, and contextual AI assistance. With ProofStudio, users can explore formal specifications and proofs across five systems without local installation, inspecting native prover feedback and experimenting with automation through a common interface.

## HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs

DevFeed: [HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs](<https://devfeed.tech/articles/hologicbench-evaluating-higher-order-logical-reasoning-in-llms-102981.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.23238>)

Author: Yucheng Wu, Jundong Xu, Mingzhen Ju, Yue Yu, Chenpeng Wang, Haoxuan Li, Liangming Pan

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [Isabelle/HOL proof assistant](<https://devfeed.tech/topics/isabelle-hol-proof-assistant.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [derivations](<https://devfeed.tech/tags/derivations.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [failure](<https://devfeed.tech/tags/failure.md>), [hol](<https://devfeed.tech/tags/hol.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llms](<https://devfeed.tech/tags/llms.md>), [logical](<https://devfeed.tech/tags/logical.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

HOLogicBench evaluates higher-order reasoning over rules and policies, an area underexplored by benchmarks focused on object-level inference. It contains 1,379 instances covering five reasoning operations, formalized in Isabelle/HOL with proof-verified answers and solver-verified reference reasoning paths. Across 16 model configurations, average accuracy was 53.86%, with the best reaching 65.99%. The authors report limited alignment between model reasoning and valid derivations, sensitivity to minimal counterfactual changes, and different failure patterns across reasoning types.

### Source excerpt

arXiv:2606.23238v3 Announce Type: replace Abstract: Existing LLM logical-reasoning benchmarks largely focus on object-level inference under fixed predicates and rules, leaving higher-order reasoning over rules and policies underexplored. We introduce HOLogicBench, a 1,379-instance benchmark that systematically evaluates five representative higher-order reasoning operations, with Isabelle/HOL formalizations and proof-verified answers. Beyond answer accuracy, HOLogicBench provides solver-verified reference reasoning paths for each instance, enabling fine-grained evaluation of model-generated reasoning against valid derivations. Across 16 model configurations, average accuracy is 53.86\%, with the best configuration reaching 65.99\%. Further analyses reveal that LLMs exhibit limited alignment with valid derivations, remain vulnerable to minimal counterfactual perturbations, and display distinct failure patterns across higher-order reasoning types.