{"ID":2858282,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08429","arxiv_id":"2510.08429","title":"ClauseLens: Clause-Grounded, CVaR-Constrained Reinforcement Learning for Trustworthy Reinsurance Pricing","abstract":"Reinsurance treaty pricing must satisfy stringent regulatory standards, yet current quoting practices remain opaque and difficult to audit. We introduce ClauseLens, a clause-grounded reinforcement learning framework that produces transparent, regulation-compliant, and risk-aware treaty quotes. ClauseLens models the quoting task as a Risk-Aware Constrained Markov Decision Process (RA-CMDP). Statutory and policy clauses are retrieved from legal and underwriting corpora, embedded into the agent's observations, and used both to constrain feasible actions and to generate clause-grounded natural language justifications. Evaluated in a multi-agent treaty simulator calibrated to industry data, ClauseLens reduces solvency violations by 51%, improves tail-risk performance by 27.9% (CVaR_0.10), and achieves 88.2% accuracy in clause-grounded explanations with retrieval precision of 87.4% and recall of 91.1%. These findings demonstrate that embedding legal context into both decision and explanation pathways yields interpretable, auditable, and regulation-aligned quoting behavior consistent with Solvency II, NAIC RBC, and the EU AI Act.","short_abstract":"Reinsurance treaty pricing must satisfy stringent regulatory standards, yet current quoting practices remain opaque and difficult to audit. We introduce ClauseLens, a clause-grounded reinforcement learning framework that produces transparent, regulation-compliant, and risk-aware treaty quotes. ClauseLens models the quo...","url_abs":"https://arxiv.org/abs/2510.08429","url_pdf":"https://arxiv.org/pdf/2510.08429v1","authors":"[\"Stella C. Dong\",\"James R. Finlay\"]","published":"2025-10-09T16:43:49Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"stat.ML\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}