Metraipolis › archive › dc_579abc3a82fd
CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis — arXiv:2608.28599
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28599
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:41:35.602Z
- SHA-256 of the archived text
93dd34dcecddd576198d00c4058a5ef8caed7c9b08bf50d20a8fdad4d8519035- Stable URL of this page
https://metraipolis.com/documento/dc_579abc3a82fd
How to cite
CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis — arXiv:2608.28599 — arXiv (en), https://arxiv.org/abs/2608.28599 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_579abc3a82fd (Metraipolis archive dc_579abc3a82fd, sha256 93dd34dcecddd576198d00c4058a5ef8caed7c9b08bf50d20a8fdad4d8519035)
BibTeX
@misc{dc579abc3a82fd,
title = {CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis — arXiv:2608.28599},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28599},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_579abc3a82fd; sha256 93dd34dcecddd576198d00c4058a5ef8caed7c9b08bf50d20a8fdad4d8519035},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28599. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Clinical diagnosis is a step-by-step, cost-aware process: a physician orders examinations one at a time, observes the results, and updates the diagnosis before reaching a final conclusion. Most medical language models instead treat diagnosis as a one-pass classification task and ignore the trade-off between a test's value and its cost. We model diagnosis as a cost-aware sequential decision process and train the policy with reinforcement learning. The main difficulty is credit assignment: the only reliable signal comes once at the end of a long trajectory, so it scores a wasteful workup the same as an efficient one. We propose CDPR (Counterfactual Diagnostic Process Reward), which needs no expert labels and no learned critic. CDPR first finds the states where the policy hesitates, using the uncertainty of its action distribution, and then scores the chosen action by its advantage over the alternatives the policy itself would consider, estimated with short rollouts under a utility that balances correctness against test count, cost, and infeasible requests. A rollout cache reuses within-batch trajectories to keep the cost low. We integrate CDPR into GRPO and test it on one in-domain (MIMIC-IV) and two out-of-domain (ClinicalBench and a private hospital dataset) benchmarks. CDPR improves diagnostic accuracy while clearly reducing the number and cost of examinations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.28599 — 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 2026-10-17T07:28:26.445Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).