2026 · Conference accepted
Agentic Reverse Engineering: From I/O to Code with Discovery Agent
Synthesizes executable programs from input/output observations using LLM-guided evolutionary search, progressively revealed examples, simple-to-complex mutations and execution-error feedback. An active variant chooses inputs and queries a hidden reference program.
Scope and limitations
IO2CodeBench has 125 generated tasks spanning basic operations, algorithms, geometry and image-to-value mappings, normally with eight visible and fifteen held-out examples. Active exploration covers a 25% subset from each level. Multimodal results average sample pass ratios, while other levels count tasks passing every held-out example. Finite test success does not establish original-source recovery or complete equivalence; arbitrary applications and stateful services are not evaluated.
Why it fits this collection
Provides a concrete observation-to-program reconstruction workflow and separates visible-example fitting from held-out behavior checks.
Publication and review details
- Venue
- NeurIPS 2026
- Status
- Conference accepted
- Publication / posting date
- 2026 (exact date not verified)
- Date source
- Official NeurIPS 2026 poster listing confirms acceptance, not a proceedings publication date. First arXiv submission was 2026-05-14; reviewed v2 was revised on 2026-10-18.
- First arXiv submission
- May 14, 2026
- arXiv
- 2605.15334
- Reviewed arXiv version
- v2
- DOI
- 10.48550/arxiv.2605.15334
The official poster and pinned repository retain the earlier title From I/O to Code with Discovery Agent; all ten authors match v2 and DataCite. The registered DOI identifies the arXiv work; no proceedings DOI or publication date is asserted. The paper uses the arXiv non-exclusive license. Author-linked code was checked at ef15827ab7090bf2d227fb1eef51d91b0163339e: its README documents Python 3.10+, provider credentials, benchmark/oracle tasks and experiment runners. No repository-wide code/data license was verified in the reviewed README and root tree. No generated programs, models or experiments were executed.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.
Primary sources
- https://arxiv.org/abs/2605.15334
- https://arxiv.org/html/2605.15334v2
- https://api.datacite.org/dois/10.48550/arxiv.2605.15334
- https://neurips.cc/virtual/2026/loc/sydney/poster/154711
- README.md GitHub · JiaruQian/IO2Code · Revision ef15827
- https://github.com/JiaruQian/IO2Code/tree/ef15827ab7090bf2d227fb1eef51d91b0163339e