# More Rounds, More Noise: Why Multi-Turn Review Fails to Improve Cross-Context Verification

arXiv: https://arxiv.org/abs/2603.16244 · HTML: https://mlsanity.com/paper/2603.16244/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 11 of 11)

- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Understanding the Dark Side of LLMs' Intrinsic Self-Correction](https://mlsanity.com/paper/2412.14959/) (2024)
- [MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning](https://mlsanity.com/paper/2409.12147/) (2024)
- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation](https://mlsanity.com/paper/2412.10424/) (2024)
- [Temporal Consistency for LLM Reasoning Process Error Identification](https://mlsanity.com/paper/2503.14495/) (2025)
- [SSR: Socratic Self-Refine for Large Language Model Reasoning](https://mlsanity.com/paper/2511.10621/) (2025)
- [Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions](https://mlsanity.com/paper/2603.12123/) (2026)

## Built on by (most cited first, 4 of 4)

- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis](https://mlsanity.com/paper/2603.21454/) (2026)
- [When Does a Second Model Help? Cross-Model Review in LLM Verification](https://mlsanity.com/paper/2610.01471/) (2026)
- [Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery](https://mlsanity.com/paper/2604.19049/) (2026)

## Abstract (arXiv)

Cross-Context Review (CCR) improves LLM verification by separating production and review into independent sessions. A natural extension is multi-turn review: letting the reviewer ask follow-up questions, receive author responses, and review again. We call this Dynamic Cross-Context Review (D-CCR). In a controlled experiment with 30 artifacts and 150 injected errors, we tested four D-CCR variants against the single-pass CCR baseline. Single-pass CCR (F1 = 0.376) significantly outperformed all multi-turn variants, including D-CCR-2b with question-and-answer exchange (F1 = 0.303, p < 0.001, d = -0.59). Multi-turn review increased recall (+0.08) but generated 62% more false positives (8.5 vs. 5.2), collapsing precision from 0.30 to 0.20. Two mechanisms drive this degradation: (1) false positive pressure -- reviewers in later rounds fabricate findings when the artifact's real errors have been exhausted, and (2) Review Target Drift -- reviewers provided with prior Q&A exchanges shift from reviewing the artifact to critiquing the conversation itself. Independent re-review without prior context (D-CCR-2c) performed worst (F1 = 0.263), confirming that mere repetition degrades rather than helps. The degradation stems from false positive pressure in additional rounds, not from information amount -- within multi-turn conditions, more information actually helps (D-CCR-2b > D-CCR-2a). The problem is not what the reviewer sees, but that reviewing again invites noise.