Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

• URL: http://arxiv.org/abs/2608.17947v1
• Date: Tue, 18 Aug 2026 16:03:22 GMT
• Title: Procedural Content Metageneration via Program Search and Continual Abstraction Discovery
• Abstract summary: We introduce Continual Abstraction Discovery, or CAD, which extracts reusable primitives from high-fitness programs into a run-specific helper module.<n>We study this approach in Sokoban, Zelda, Dangerous Dave, and Lode Runner.
• Score: 3.899863694644006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dave, and Lode Runner. Each run evolves complete Python generators through language-model mutation and crossover. We introduce Continual Abstraction Discovery, or CAD, which extracts reusable primitives from high-fitness programs into a run-specific helper module. A 2x2 experiment crosses CAD with access to a fixed hand-written domain API. The completed data set contains 160 complete runs, with at least ten 50-generation runs in every cell. CAD raises mean final best fitness in all eight domain and API comparisons. Across all CAD runs, learned libraries are adopted by most later programs and repeatedly rediscover validation, reachability, and structural utilities. These results support that discovering reusable primitives improves evolutionary program search for content generators.

Related papers

• Qwen-CUA: Native Computer Use for (almost) Everything [104.78368489343713]
  We introduce Qwen-CUA, a native computer-use agent with a mixture-of-experts backbone.<n>It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs.<n>Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence.
  arXiv  Detail & Related papers  (2026-08-03T15:04:20Z)
• SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation [10.98670245879463]
  We present SciCodePile, the largest scientific code corpus to date, constructed from 37,737 public repositories.<n>We evaluate 15 large language models (LLMs) on three tasks: prefix-to-suffix completion, fill-in-the-middle infilling, and executable code generation.
  arXiv  Detail & Related papers  (2026-07-21T13:46:52Z)
• Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation [83.53893718885796]
  Visual generators excel at rendering, but they confidently fabricate what they do not know.<n>We construct SearchGen-20K and SearchGen-Bench, with 20,839 prompts spanning twelve failure categories and twenty-two domains.<n>On SearchGen-Bench, frontier open generators score only 21 to 28 out of 100, a 40-point collapse invisible to existing benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:56:12Z)
• FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories [0.0]
  We introduce FllumaOne, a code-native multimodal CAD dataset.<n>The dataset supports conditioned CAD reconstruction, executable program, feature-tree prediction, B-Rep analysis, retrieval, design completion, and editable reverse engineering.
  arXiv  Detail & Related papers  (2026-06-16T09:09:59Z)
• AcademiClaw: When Students Set Challenges for AI Agents [69.70303995121154]
  AcademiClaw is a benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic disconnects.<n>We show that even the best of models achieves only a 55% pass rate.<n>We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community.
  arXiv  Detail & Related papers  (2026-05-04T14:40:42Z)
• ExecRepoBench: Multi-level Executable Code Completion Evaluation [45.963424627710765]
  We introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench.<n>We present a multi-level grammar-based completion methodology conditioned on the abstract syntax tree to mask code fragments at various logical units.<n>Then, we fine-tune the open-source LLM with 7B parameters on Repo-Instruct to produce a strong code completion baseline model Qwen2.5-Coder-Instruct-C.
  arXiv  Detail & Related papers  (2024-12-16T17:14:35Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Learning to Reason via Program Generation, Emulation, and Search [33.11955431589091]
  Program synthesis with language models (LMs) has unlocked a large set of reasoning abilities. Not all reasoning tasks are easily expressible as code, e.g. tasks involving commonsense reasoning, moral decision-making, and sarcasm understanding. We propose Code Generation and Emulated EXecution (CoGEX) to extend an LM's program synthesis skills to such tasks.
  arXiv  Detail & Related papers  (2024-05-25T19:40:50Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks [132.29772160843825]
  Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions. Existing methods have used the same generating architecture for all classes. This paper presents a novel idea that adopts NAS to find a distinct architecture for each class.
  arXiv  Detail & Related papers  (2020-06-25T07:05:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.