Property-Guided LLM Program Synthesis for Planning
The paper discusses a novel approach to program synthesis using property-guided LLMs. This method improves efficiency by providing concrete counterexamples when a program fails to meet defined properties. The results show significant reductions in program generation and evaluation costs while enhancing the quality of synthesized programs.
- ▪Property-guided LLM program synthesis checks if a candidate satisfies a formally defined property.
- ▪When a property is violated, the system provides a counterexample, reducing the need for extensive program generation.
- ▪The approach was evaluated on ten planning domains, generating seven times fewer programs on average compared to prior methods.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.16142 |
| Publication time | Mon, 18 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-18T04:04:54.418Z |
| Last seen | 2026-05-18T04:04:54.418Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | PxA18_4YQtCh |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.16142 (cs) [Submitted on 15 May 2026] Title:Property-Guided LLM Program Synthesis for Planning Authors:Augusto B. Corrêa, André G. Pereira, Jendrik Seipp View a PDF of the paper titled Property-Guided LLM Program Synthesis for Planning, by Augusto B. Corr\^ea and 2 other authors View PDF HTML (experimental) Abstract:LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple numeric scores to signal program quality, such as the value of the solution or the number of passed tests.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
