Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2507.11198

Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding

Conrad Borchers·Bahar Shahrokhian·Francesco Balzan·Elham Tajik·Sreecharan Sankaranarayanan·Sebastian Simon
View original source ↗Read source document ↗Export metadata ↓

Abstract

Large Language Models (LLMs) enable new possibilities for qualitative research at scale, including annotation and qualitative coding of educational data. While LLM-based multi-agent systems (MAS) can emulate human coding workflows, their benefits over single LLM agents for coding remain poorly understood. To that end, we conducted an experimental study of how persona and temperature of component agents of a MAS shapes consensus-building and coding accuracy for dialog segments. LLMs were prompted to code these segments deductively using a mature codebook with 8 codes and high inter-rater reliability derived from prior research. Our open-source MAS mirrors deductive human coding through structured agent discussion and consensus arbitration. Using six open-source LLMs (with 3 to 32 billion parameters) and 18 experimental configurations, we analyze over 77,000 coding decisions against a gold-standard dataset of human-annotated transcripts from online math tutoring sessions facilitated by educational software. Temperature significantly impacted whether and when consensus was reached across all six LLMs. MAS with multiple personas (including neutral, assertive, or empathetic) significantly delayed consensus in four out of six LLMs compared to uniform personas. In three of those LLMs, higher temperatures significantly diminished the effects of multiple personas on consensus. However, neither temperature nor persona pairing led to robust improvements in coding accuracy. Single agents matched or outperformed MAS consensus in most conditions. Qualitative analysis of MAS collaboration and coding disagreement may, however, improve codebook design and human-AI coding.

Explore related subjects

cs.CLcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Conrad Borchers, Bahar Shahrokhian, Francesco Balzan, Elham Tajik, Sreecharan Sankaranarayanan, Sebastian Simon. 2026-05-10. Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding. https://arxiv.org/abs/2507.11198

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration

Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable pretraining methods. One notable advancement in this area is the Cramming technique (Geiping and Goldstein, 2022), which enables the pretraining of BERT-style language models using just one GPU in a single day. Building on this innovative approach, we introduce the Dependency Agreement Cramming (DA-Cramming), an efficient framework that integrates information about dependency agreements into the pretraining process. Unlike existing methods that leverage similar semantic information during finetuning, our approach represents a pioneering effort focusing on enhancing the foundational language understanding with semantic information during pretraining. We meticulously design a dual-stage pretraining work flow with four dedicated submodels to capture representative dependency agreements at the chunk level, effectively transforming these agreements into embeddings to benefit the pretraining. Extensive empirical results demonstrate that our method significantly outperforms previous methods across various tasks.

cs.CL↗
arXiv2026

BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?

We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities. This benchmark addresses the gap in current evaluations that often overlook the ability of models to comprehend and produce code constrained by computational complexity. BigO(Bench) includes tooling to infer the algorithmic complexity of any Python function from profiling measurements, including human- or LLM-generated solutions. BigO(Bench) also includes of set of 3,105 coding problems and 1,190,250 solutions from Code Contests annotated with inferred (synthetic) time and space complexity labels from the complexity framework, as well as corresponding runtime and memory footprint values for a large set of input sizes. We present results from evaluating multiple state-of-the-art language models on this benchmark, highlighting their strengths and weaknesses in handling complexity requirements. In particular, token-space reasoning models are unrivaled in code generation but not in complexity understanding, hinting that they may not generalize well to tasks for which no reward was given at training time.

cs.CL↗
arXiv2026

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning. However, existing attempts to unify these paradigms remain narrow in scope, typically limited to open-domain QA with fixed retrieval settings, which constrains generalization to broader domains. To address this limitation, we propose UR$^2$ (Unified RAG and Reasoning)), a general reinforcement learning framework that dynamically coordinates retrieval and reasoning. UR$^2$ introduces two key designs: a difficulty-aware curriculum that selectively invokes retrieval only for challenging instances, and a hybrid knowledge access strategy that combines domain-specific offline corpora with on-the-fly LLM-generated summaries. Together, these components mitigate the imbalance between retrieval and reasoning and improve robustness to noisy information. Experiments on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks show that UR$^2$, built on Qwen-2.5-3/7B and LLaMA-3.1-8B, consistently outperforms existing RAG and RL baselines, and achieves performance comparable to GPT-4o-mini and GPT-4.1-mini on several benchmarks. Code, models, and data are available at https://github.com/Tsinghua-dhy/UR2.

cs.CL↗