Metraipolis › archive › dc_abbbefbf16ae

Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination — arXiv:2610.33503

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33503
License (as archived): CC0-1.0
Archived: 2026-10-27T08:00:12.790Z
SHA-256 of the archived text: b6bf03fcff1bab4ad48a5f515de67862b693a1b9c06b2c10dfdec8d9ba2ade5e
Stable URL of this page: https://metraipolis.com/documento/dc_abbbefbf16ae

How to cite

Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination — arXiv:2610.33503 — arXiv (en), https://arxiv.org/abs/2610.33503 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abbbefbf16ae (Metraipolis archive dc_abbbefbf16ae, sha256 b6bf03fcff1bab4ad48a5f515de67862b693a1b9c06b2c10dfdec8d9ba2ade5e)

BibTeX

@misc{dcabbbefbf16ae,
  title = {Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination — arXiv:2610.33503},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33503},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abbbefbf16ae; sha256 b6bf03fcff1bab4ad48a5f515de67862b693a1b9c06b2c10dfdec8d9ba2ade5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33503. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments documented in Office Actions (OAs) across heterogeneous scientific and technical domains. However, existing benchmarks largely focus on static and limited candidate sets, leaving the full search--reasoning--assessment process underexplored. We present PatEx-Gym, the first framework for developing and evaluating agents for patent examination, which integrates three components. First, PatEx-Bench provides 1K realistic examination tasks, two large-scale retrieval corpora containing over 1M patents and 52K scientific papers, and a harness runtime supporting iterative search, document visits, reasoning, and OA generation. Second, we introduce PASS, an annotation-free Prior-Art Agentic Search Trajectory Synthesis framework. Specifically, it exploits document visits as implicit relevance signals and evidence-acquisition anchors to model intra-turn query behavior, inter-turn search progression, and trajectory-level evidence and outcome quality, yielding PatEx-SynData. Third, we train PatEx-Agent at the 4B scale via supervised fine-tuning on the curated trajectories, establishing a lightweight baseline. Extensive experiments show that final decision accuracy alone does not fully reflect examination quality, while prior-art discovery remains difficult even for strong frontier models. Our PatEx-Agent achieves competitive performance against substantially larger general-purpose agents. These results show that training on PatEx-SynData enables a compact 4B model to serve as a competitive baseline for prior-art search and patent examination. We view patent examination as a demanding testbed for agentic search and deep research agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.33503 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:30.829Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).