# LLMs Can Generate a Better Answer by Aggregating Their Own Responses

arXiv: https://arxiv.org/abs/2503.04104 · HTML: https://mlsanity.com/paper/2503.04104/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 37 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (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)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [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)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)

## Built on by (most cited first, 27 of 27)

- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models](https://mlsanity.com/paper/2509.26626/) (2025)
- [AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks](https://mlsanity.com/paper/2508.00890/) (2025)
- [TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture](https://mlsanity.com/paper/2510.01279/) (2025)
- [Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs](https://mlsanity.com/paper/2509.00084/) (2025)
- [Efficient Test-Time Scaling for Small Vision-Language Models](https://mlsanity.com/paper/2510.03574/) (2025)
- [V1: Unifying Generation and Self-Verification for Parallel Reasoners](https://mlsanity.com/paper/2603.04304/) (2026)
- [Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking](https://mlsanity.com/paper/2510.26122/) (2025)
- [Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution](https://mlsanity.com/paper/2604.07725/) (2026)
- [Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning](https://mlsanity.com/paper/2512.02874/) (2025)
- [Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph](https://mlsanity.com/paper/2511.00086/) (2025)
- [Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models](https://mlsanity.com/paper/2604.05868/) (2026)
- [On Test-Time Scaling for Vision-Language Models](https://mlsanity.com/paper/2606.28864/) (2026)
- [MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge](https://mlsanity.com/paper/2505.23982/) (2025)
- [Knowing What's Missing: Assessing Information Sufficiency in Question Answering](https://mlsanity.com/paper/2512.06476/) (2025)
- [Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesis](https://mlsanity.com/paper/2601.16596/) (2026)
- [Multi-Agent Systems Should be Treated as Principal-Agent Problems](https://mlsanity.com/paper/2601.23211/) (2026)
- [SPIRAL: Learning to Search and Aggregate](https://mlsanity.com/paper/2606.23595/) (2026)
- [Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge](https://mlsanity.com/paper/2512.03019/) (2025)
- [From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs](https://mlsanity.com/paper/2509.23196/) (2025)
- [Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias](https://mlsanity.com/paper/2604.02923/) (2026)
- [In-Context Compositional Learning via Sparse Coding Transformer](https://mlsanity.com/paper/2511.20194/) (2025)
- [CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation](https://mlsanity.com/paper/2601.08010/) (2026)
- [SCATR: Simple Calibrated Test-Time Ranking](https://mlsanity.com/paper/2604.16535/) (2026)
- [Generating Public Health Responses using Survey-Augmented Large Language Models](https://mlsanity.com/paper/2606.21820/) (2026)
- [Performance Foundations of Parallel & Distributed Reasoning Language Models](https://mlsanity.com/paper/2608.27046/) (2026)
- [An Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration Architectures](https://mlsanity.com/paper/2609.36104/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems. While approaches like self-correction and response selection have emerged as popular solutions, recent studies have shown these methods perform poorly when relying on the LLM itself to provide feedback or selection criteria. We argue this limitation stems from the fact that common LLM post-training procedures lack explicit supervision for discriminative judgment tasks. In this paper, we propose Generative Self-Aggregation (GSA), a novel prompting method that improves answer quality without requiring the model's discriminative capabilities. GSA first samples multiple diverse responses from the LLM, then aggregates them to obtain an improved solution. Unlike previous approaches, our method does not require the LLM to correct errors or compare response quality; instead, it leverages the model's generative abilities to synthesize a new response based on the context of multiple samples. While GSA shares similarities with the self-consistency (SC) approach for response aggregation, SC requires specific verifiable tokens to enable majority voting. In contrast, our approach is more general and can be applied to open-ended tasks. Empirical evaluation demonstrates that GSA effectively improves response quality across various tasks, including mathematical reasoning, knowledge-based problems, and open-ended generation tasks such as code synthesis and conversational responses.