Skip to content
← Back to explorer

Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent

Bingxuan Li, Simo Du, Yue Guo · Apr 8, 2026 · Citations: 0

Automatic Metrics Long Horizon Medicine
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 8, 2026, 4:32 PM

Fresh

Extraction refreshed

Apr 10, 2026, 7:13 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns. Recent LLMs-based diagnostic agents have shown promising progress in clinical reasoning for decision support. However, most approaches treat cases independently, limiting experience reuse and continual adaptation. We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module. We design a reinforcement training framework tailored to our designed agent for joint optimization of reasoning and memory management. We evaluate SEA in two complementary settings. On standard evaluation with MedCaseReasoning dataset, SEA achieves 92.46% accuracy, outperforming the strongest baseline by +19.6%, demonstrating the benefit of jointly optimizing reasoning and memory. On the long-horizon with ER-Reason dataset, SEA attains the best final accuracy (0.7214) and the largest improvement (+0.35 Acc@100), while baseline methods show limited or unstable gains. Expert evaluation further indicates that rules consolidated from SEA show strong clinical correctness, usefulness and trust, suggesting that the induced rules in dual-memory module are reliable and practically meaningful. Overall, SEA improves both diagnostic reasoning ability and continual learning by effectively transforming experience into reusable knowledge.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction confidence is 0.45 (below strong-reference threshold).

Trust level

Low

Eval-Fit Score

25/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns.

Reported Metrics

partial

Accuracy

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: On standard evaluation with MedCaseReasoning dataset, SEA achieves 92.46% accuracy, outperforming the strongest baseline by +19.6%, demonstrating the benefit of jointly optimizing reasoning and memory.

Rater Population

partial

Domain Experts

Confidence: Low Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Domain Experts
  • Unit of annotation: Unknown
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Long Horizon
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module. HFEPX signals include Automatic Metrics, Long Horizon with confidence 0.45. Updated from current HFEPX corpus.

Generated Apr 10, 2026, 7:13 AM · Grounded in abstract + metadata only

Key Takeaways

  • We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module.
  • We evaluate SEA in two complementary settings.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module.
  • We evaluate SEA in two complementary settings.
  • On standard evaluation with MedCaseReasoning dataset, SEA achieves 92.46% accuracy, outperforming the strongest baseline by +19.6%, demonstrating the benefit of jointly optimizing reasoning and memory.

Why It Matters For Eval

  • We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module.
  • On standard evaluation with MedCaseReasoning dataset, SEA achieves 92.46% accuracy, outperforming the strongest baseline by +19.6%, demonstrating the benefit of jointly optimizing reasoning and memory.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote