Metraipolis › archive › dc_fa0638b72b11
CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents — arXiv:2608.22899
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22899
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:41:41.439Z
- SHA-256 of the archived text
398e138e69fe8fb8f20dce640ee9e7201dfb78e696d83951aeebcd6abaae9938- Stable URL of this page
https://metraipolis.com/documento/dc_fa0638b72b11
How to cite
CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents — arXiv:2608.22899 — arXiv (en), https://arxiv.org/abs/2608.22899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa0638b72b11 (Metraipolis archive dc_fa0638b72b11, sha256 398e138e69fe8fb8f20dce640ee9e7201dfb78e696d83951aeebcd6abaae9938)
BibTeX
@misc{dcfa0638b72b11,
title = {CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents — arXiv:2608.22899},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22899},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa0638b72b11; sha256 398e138e69fe8fb8f20dce640ee9e7201dfb78e696d83951aeebcd6abaae9938},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Unlike static medical question answering, long-horizon diagnosis captures the sequential nature of clinical practice: evidence is progressively acquired, integrated, and evaluated over multiple rounds of interaction before reaching a final diagnosis. However, existing doctor agents often fail when critical evidence is either not acquired or not adequately incorporated into diagnostic reasoning. Recent agentic approaches attempt to address these failures by reusing historical trajectories or distilled memories. But their diagnostic gains remain constrained because such experience may contain noisy or incidental information and is typically reused without validating which evidence actually drives diagnostic decisions. To address this limitation, we introduce CDEG, a graph-based framework that learns reusable decision-critical evidence from historical diagnostic trajectories. CDEG contrasts successful and failed trajectories from the same case to identify candidate evidence, validates their diagnostic impact through controlled counterfactual interventions, and organizes the resulting diagnosis--evidence--action relations into a structured graph. During inference, CDEG tracks the evolving patient evidence state to retrieve relevant diagnostic relations and selectively guide missing evidence acquisition or overlooked evidence reappraisal. Across in-domain and out-of-distribution benchmarks with multiple doctor agent backbones, CDEG consistently improves diagnostic performance, achieving up to an 11.5% accuracy gain over vanilla agents. These results demonstrate that reliable long-horizon diagnosis requires moving beyond trajectory-level experience reuse toward evidence-level learning of the factors that truly shape clinical decisions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22899 — 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 2026-10-18T07:37:52.750Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).