# Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

arXiv: https://arxiv.org/abs/2604.01029 · HTML: https://mlsanity.com/paper/2604.01029/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems](https://mlsanity.com/paper/2310.12397/) (2023)
- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models](https://mlsanity.com/paper/2402.12563/) (2024)
- [LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints](https://mlsanity.com/paper/2410.06458/) (2024)
- [SCREWS: A Modular Framework for Reasoning with Revisions](https://mlsanity.com/paper/2309.13075/) (2023)
- [SSR: Socratic Self-Refine for Large Language Model Reasoning](https://mlsanity.com/paper/2511.10621/) (2025)
- [Re2: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving](https://mlsanity.com/paper/2603.07197/) (2026)
- [Less LLM, More Documents: Searching for Improved RAG](https://mlsanity.com/paper/2510.02657/) (2025)
- [Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests](https://mlsanity.com/paper/2601.17617/) (2026)

## Built on by (most cited first, 7 of 7)

- [Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer](https://mlsanity.com/paper/2607.17100/) (2026)
- [Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents](https://mlsanity.com/paper/2609.09219/) (2026)
- [Return or Revise? Learning When Revision Helps Retrieval-Augmented QA](https://mlsanity.com/paper/2609.30087/) (2026)
- [ControlScope: Workflow Revision and Reliability in LLM Agents](https://mlsanity.com/paper/2609.34313/) (2026)
- [The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents](https://mlsanity.com/paper/2609.36829/) (2026)
- [Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts](https://mlsanity.com/paper/2610.00314/) (2026)
- [Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization](https://mlsanity.com/paper/2610.01017/) (2026)

## Abstract (arXiv)

Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction. We question this assumption with a controlled decomposition experiment that uses four matched conditions to separate second-pass gains into three additive components: re-solving, scaffold, and content. We evaluate this design across two model pairs on three benchmarks spanning knowledge-intensive MCQ and competitive programming. Our results show that the gains of multi-LLM revision are not monolithic, but depend on task structure, draft quality, and the type of draft information. On MCQ tasks, where the answer space is constrained and drafts provide little structural guidance, most gains are consistent with stronger-model re-solving, and directly routing queries to the stronger model can be more effective than revising a weak draft. On code generation tasks, however, two-stage prompting remains useful because even semantically null drafts can provide substantial structural scaffolding, while weak draft content can be harmful. Finally, role-reversed experiments show that strong drafts clearly benefit weak reviewers. Ultimately, our findings demonstrate that the utility of multi-LLM revision is dynamically bottlenecked by task structure and draft quality, necessitating more targeted pipeline designs rather than blanket revision strategies.