COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

arXiv:2605.15016 · cs.CL, cs.AI · Submitted 2026-05-14 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-14

Updated: 2026-09-26

Code: https://github.com/FrankDengAI/COTCAgent

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Sequential diagnosis requires ranking diseases from a sparse intake under a public budget of follow-up questions, which is diagnostic triage with missing findings rather than screening of people who

Terminology

Abstract

Sequential diagnosis requires ranking diseases from a sparse intake under a public budget of follow-up questions, which is diagnostic triage with missing findings rather than screening of people who have no symptoms. Because laboratory series arrive irregularly and histories remain incomplete, the ranking must be updated as new facts arrive, yet most pipelines are limited by unnamed numeric trends, unverifiable free-form chain of thought, and a negative bias from treating unasked findings as absent. To solve these, we propose COTCAgent, a sparse-intake consultation agent built on Chain-of-Thought Completion (COTC), which couples three modules on one shared ternary evidence log. The Temporal-Statistics Adapter (TSA) turns time series into typed predicates with named statistics, while the COTC module scores diseases with a learnable knowledge-base energy in which unknown findings add zero energy, after which bounded probabilistic completion selects unknown findings under the question budget and writes each answer back as present, absent, or unknown. Edge strengths and an absence scale are trained with listwise ranking under a sparse curriculum, so that the same energy chooses the next finding by a surrogate entropy reduction. Experiments on DDXPlus and MIMIC-IV show that these modules improve ranking under a matched question budget, with information-gain completion above asking nothing or at random and above protocol-matched askers and a local LLM, thereby providing a foundation for future calibrated scoring and prospective preventive consultation.

Sources

Related papers