Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior

• URL: http://arxiv.org/abs/2606.20632v2
• Date: Wed, 24 Jun 2026 20:00:19 GMT
• Title: Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior
• Abstract summary: We study whether the same family label predicts behavior in interactive multi-LLM systems.<n>We find that hedging, a reasoning-distilled Llama checkpoint shifts by 18% depending on which same-base partner it replies to.<n>Results identify post-training recipe as a first-class axis for multi-LLM panel composition.
• Score: 16.249731576262167
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordinate as agents. Their value depends on the models producing measurably different conversational behaviors when given the same input. Prior offline studies recommend drawing one model per family for behavioral diversity, because LLMs prefer outputs from their own family when rating one another in isolation. Whether the same family label predicts behavior in interactive multi-LLM systems, the setting that real deployed systems use, has not been tested. We study this with a 940,000-chain 11-checkpoint corpus and a 1.6M-chain same-base Llama factorial. On our validated headline metric, hedging, a reasoning-distilled Llama checkpoint shifts by 18% depending on which same-base partner it replies to, more than any cross-family hedging gap in the controlled subset. Qwen, closed-API, and runtime checks suggest the pattern is not isolated, while repair and challenge analyses remain exploratory because their surface-cue detectors are weaker. Overall, the results identify post-training recipe as a first-class axis for multi-LLM panel composition and show that model family alone is an incomplete proxy for conversational diversity.

Related papers

• Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling [65.03665015319457]
  We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two modes: action-class miscalibration and action-execution failure.<n>We validate it on a panel of tool-calling models across multiple multi-turn benchmarks.
  arXiv  Detail & Related papers  (2026-09-01T09:08:15Z)
• Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases [0.0]
  We introduce an analytically exact framework for the controlled behavioral evaluation of Large Language Models (LLMs)<n>We replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects.<n>We derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically.<n>We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.
  arXiv  Detail & Related papers  (2026-08-11T05:20:06Z)
• Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models [29.673427534201654]
  We introduce Facet-Probe, a five-facet audit of multimodal large language models.<n>We find that none of the 18 MLLMs we audit are order-invariant.<n>We propose cross-ordering flip rate as a standard reporting axis for MLLMs.
  arXiv  Detail & Related papers  (2026-06-24T17:53:26Z)
• Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data [54.145424717168794]
  Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored.<n>This paper presents a case study to investigate LLM-based individual simulation with a volunteer-contributed archive of private messaging history spanning over ten years.<n>We propose the "Individual Turing Test" to evaluate whether acquaintances of the volunteer can correctly identify which response in a multi-candidate pool most plausibly comes from the volunteer.
  arXiv  Detail & Related papers  (2026-03-01T21:46:27Z)
• Learning to Trust the Crowd: A Multi-Model Consensus Reasoning Engine for Large Language Models [0.0]
  Large language models (LLMs) achieve strong aver- age performance yet remain unreliable at the instance level.<n>We introduce a Multi-Model Consensus Reasoning Engine that treats the set of LLM outputs as input to a supervised meta-learner.<n>The system maps natural language responses into structured features using semantic embeddings, pairwise similarity and clustering statistics, lexical and structural cues, reasoning-quality scores, confidence estimates, and model-specific priors.
  arXiv  Detail & Related papers  (2026-01-12T06:27:06Z)
• When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers [11.937771430269201]
  We present a systematic study across 37 large language models (LLMs)<n>We compare self-verification with verification within the same family and across different families.<n>We analyze how metrics like verifier gain and false positive rate scale with model size and post-training, and characterize differences in dataset verifiability.
  arXiv  Detail & Related papers  (2025-12-02T00:51:14Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Multi-LLM QA with Embodied Exploration [55.581423861790945]
  We investigate the use of Multi-Embodied LLM Explorers (MELE) for question-answering in an unknown environment. Multiple LLM-based agents independently explore and then answer queries about a household environment. We analyze different aggregation methods to generate a single, final answer for each query.
  arXiv  Detail & Related papers  (2024-06-16T12:46:40Z)
• Do Membership Inference Attacks Work on Large Language Models? [141.2019867466968]
  Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. We perform a large-scale evaluation of MIAs over a suite of language models trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across varying LLM sizes and domains.
  arXiv  Detail & Related papers  (2024-02-12T17:52:05Z)
• Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning [14.569770617709073]
  We present a detailed analysis of which design choices cause instabilities and inconsistencies in task predictions. We show how spurious correlations between input distributions and labels form only a minor problem for prompted models. We statistically analyse the results to show which factors are the most influential, interactive or stable.
  arXiv  Detail & Related papers  (2023-10-20T13:25:24Z)
• Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency [127.97467912117652]
  Large language models (LLMs) have exhibited remarkable ability in code generation. However, generating the correct solution in a single attempt still remains a challenge. We propose the Multi-Perspective Self-Consistency (MPSC) framework incorporating both inter- and intra-consistency.
  arXiv  Detail & Related papers  (2023-09-29T14:23:26Z)
• Multifamily Malware Models [5.414308305392762]
  We conduct experiments based on byte $n$-gram features to quantify the relationship between the generality of the training dataset and the accuracy of the corresponding machine learning models. We find that neighborhood-based algorithms generalize surprisingly well, far outperforming the other machine learning techniques considered.
  arXiv  Detail & Related papers  (2022-06-27T13:06:31Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.