# When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search

arXiv: https://arxiv.org/abs/2609.24101 · HTML: https://mlsanity.com/paper/2609.24101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis](https://mlsanity.com/paper/2412.16833/) (2024)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [Biolink Model: A Universal Schema for Knowledge Graphs in Clinical, Biomedical, and Translational Science](https://mlsanity.com/paper/2203.13906/) (2022)
- [KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs](https://mlsanity.com/paper/2507.02773/) (2025)
- [BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science](https://mlsanity.com/paper/2407.00466/) (2024)
- [MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph](https://mlsanity.com/paper/2508.12393/) (2025)

## Abstract (arXiv)

Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper retrieval can therefore make a system more likely to falsely infer benefit when the true effect is null. We formalise this phenomenon as evidence drift and prove that, under a standard publication-bias model, the false-positive probability on null-effect queries follows a strictly increasing large-sample envelope in retrieval depth, approaching one. Empirically, on a held-out test set of 140 Cochrane-derived queries, drift rises monotonically from 7.9% to 15.7% as the retrieval budget grows from 3 to 20 steps, and concentrates in the null-effect class. We present DACG-agent, a drift-aware causal-graph agent that incrementally builds a causal knowledge graph from PubMed abstracts and applies a two-layer stopping policy with complementary roles: a KL-divergence monitor that detects posterior convergence (the accuracy layer), and a Bradley--Terry process reward model (PRM) whose online decline detection halts retrieval once evidence quality peaks (the efficiency layer). Against full-budget retrieval, DACG-agent reduces evidence drift from 15.7% to 6.4% and improves null-effect accuracy by 21 percentage points (40.0%→61.4%) while using 67% fewer retrieval steps; overall accuracy rises from 61.4% to 69.3% (95% CI 61--77). A simulation confirms the drift result transfers from the analysed vote-counting aggregator to the deployed noisy-OR one.