Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination

• URL: http://arxiv.org/abs/2608.04618v1
• Date: Wed, 05 Aug 2026 09:24:39 GMT
• Title: Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination
• Abstract summary: We decouple candidate headroom from replacement authority, rendering the latter as an explicit, auditable object.<n>Our proposed method, Agreement-Before-Diversity, is a frozen, label-free decision rule.
• Score: 11.215813718564283
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Heterogeneous language-model ensembles expand the space of candidate responses, yet they lack a principled criterion for when a newly generated answer should supersede an already supported one. We decouple candidate headroom from replacement authority, rendering the latter as an explicit, auditable object. Our proposed method, Agreement-Before-Diversity (ABD), is a frozen, label-free decision rule: an anchor answer is retained if two additional trusted samples corroborate it under a fixed equivalence relation; otherwise, it is replaced by a heterogeneous synthesis. For this gating mechanism, we prove two exact identities. The first shows that the accuracy gap relative to unconditional synthesis is determined jointly by the agreement coverage and the anchor's advantage on the protected subset. The second shows that the gap relative to never synthesizing reflects a contrast between authorized recovery and authorized destruction. Neither identity assumes independence or calibrated confidence, and the expected inference cost is approximately eight minus five times the coverage in number of calls. Under blind, exact-ID evaluation, ABD achieves 59.43% on the complete LiveCodeBench-v6 (vs. 52.57% for Single9 and 52.00% for HAC; n = 175) and 75.00% on an untouched GPQA-Diamond split (both controls at 72.78%; n = 180). Furthermore, these identities localize every aggregate difference to an enumerable protected stratum: no discordant items occur among the 3 protected cases on LiveCodeBench, where coverage bounds the gate's contribution to 1.71 points a priori; 13 versus 8 discordant cases among 132 on GPQA-Diamond; and 12 versus 0 among 71 under a frozen anchor perturbation. Diversity supplies potential; verification structure supplies authority.

Related papers

• Observational Indistinguishability and Integrity Blind Regions in Hybrid Quantum-Classical Workflows [0.0]
  We present a claim-relative evidence/reference framework for hybrid quantum-classical workflow integrity.<n> Observational indistinguishability yields structural blind regions, distinct from finite-batch statistical misses.
  arXiv  Detail & Related papers  (2026-09-15T13:16:37Z)
• Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification [14.108900142001628]
  We introduce Relation-Orbit, a closed-form contrast that assigns eight normalized likelihoods to query-supporting and counterfactual roles.<n>On VSR and GQA across four frozen vision-language models, Relation-Orbit yields higher mean test coverage at a 10% selective-risk calibration target.
  arXiv  Detail & Related papers  (2026-09-15T11:19:03Z)
• Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration [10.293646536158302]
  PACT treats evidence countability as a relational variable for provenance-conserving fusion and typed action admission.<n>Across 31,200 evaluations in 48 scene clusters, PACT attains a common-support normalized risk-coverage area (ncsAURC) of 0.0861.<n>On complete-source records, native scores favor PACT, but a common posterior-peak score narrows its difference from nested Dirichlet and favors product fusion.
  arXiv  Detail & Related papers  (2026-08-31T21:21:35Z)
• Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit [0.0]
  Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network.<n>For a twice-differentiable readout, the open-path order-swap decomposes into a canonical additive response measured by single interventions.<n>Across six open-weight language-model families, the single-intervention baseline explains 84.3-97.7 percent of the bracket norm.
  arXiv  Detail & Related papers  (2026-08-26T02:54:02Z)
• Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation [6.047519836191728]
  We formalize a protocol-level identifiability audit over a finite behavioral policy class.<n>The audit requires zero model calls and resolves our diagnostic case.<n>This case shows how evaluation-design validity can be checked structurally before model inference.
  arXiv  Detail & Related papers  (2026-08-13T14:49:47Z)
• When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives [0.0]
  We operationalize dispersion-revision coupling in collective intelligence research.<n>We show that conditional dissent improves false-premise recovery by +17.7 points.<n>We recommend reporting per-intervention stance shift and premise-preservation rate alongside accuracy.
  arXiv  Detail & Related papers  (2026-08-04T14:19:59Z)
• PriorProof: A Point-in-Time Measure of Technique Novelty for Formal Proofs [0.23689955632456092]
  We study a deliberately narrower construct: time-relative proof-route nonstandardness in formal mathematics.<n>PriorProof extracts the dependency footprint of its elaborated proof term and scores the weighted surprisal of that footprint.<n>We present PriorProof as a decomposable, time-anchored signal whose score gap provides an interpretable reliability indicator.
  arXiv  Detail & Related papers  (2026-07-18T23:10:00Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking [22.825786049667602]
  We propose a replication-first paradigm to anchor validity to a single human-rater consensus.<n>We certify the instrument via four properties -- reliability across K runs, cross-instrument replication across architecturally distinct judges, historical-footprint calibration via judges from earlier training cohorts, and pre-registered prediction.<n>We test it on emotional accompaniment by letting the self-evolve data-driven across: the dimensions are not pre-stipulated and the procedure stabilizes to a 9-dimension set.
  arXiv  Detail & Related papers  (2026-05-27T03:41:11Z)
• The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning [0.5854803320592717]
  We prove optimality in a linear-Gaussian model (Thm. A), necessity of range coverage for any quadratic penalty that zeros deployment drift (Thm. G)<n>Thirteen blocks (ML through Qwen2.5-7B) test matched vs isotropic vs wrong-direction penalties on geometry and deployment drift.<n>We claim a falsifiable design recipe: estimate Sigma_task, match Sigma', run the controls, report task and geometry separately.
  arXiv  Detail & Related papers  (2026-05-21T17:53:28Z)
• Towards Context-Invariant Safety Alignment for Large Language Models [37.23800025875439]
  We introduce Anchor Invariance Regularization (AIR), which treats verifiable prompts as anchors and uses a stop-gradient target to regularize only the open-ended variants toward the anchor performance.<n>AIR boosts in-distribution group accuracy by 12.71% and out-of-distribution consistency by 33.49%, making safety constraints robust to adversarial framings.
  arXiv  Detail & Related papers  (2026-05-20T10:33:11Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Contrastive Identification and Generation in the Limit [39.91890433860882]
  We study contrastive identification and generation in the limit, where the learner observes a contrastive presentation of data.<n>We prove a sharp reversal under adversarial corruption: there exist classes identifiable from contrastive pairs under any finite corruption budget.<n>The unifying technical object is the common crossing graph, which encodes pairwise ambiguity, family-level generation obstructions, and corruption defects in a single coverage-and-incidence language.
  arXiv  Detail & Related papers  (2026-05-07T13:14:51Z)
• Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation [0.0]
  Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation.<n>They suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value perspectives.<n>We present the AI Council, a three-phase deliberation framework, and conduct 120 deliberations across two policy scenarios to test two interventions.
  arXiv  Detail & Related papers  (2026-04-29T11:47:28Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• Conditional Coverage Diagnostics for Conformal Prediction [47.93989136542648]
  We show that conditional coverage estimation can be a classification problem.<n>We call the resulting family of metrics excess risk of the target coverage (ERT)<n>We release an open-source package for ERT as well as previous conditional coverage metrics.
  arXiv  Detail & Related papers  (2025-12-12T18:47:39Z)
• Fortytwo: Swarm Inference with Peer-Ranked Consensus [36.94429692322632]
  We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference.<n>Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting.
  arXiv  Detail & Related papers  (2025-10-27T23:19:48Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• A Weaker Faithfulness Assumption based on Triple Interactions [89.59955143854556]
  We propose a weaker assumption that we call $2$-adjacency faithfulness. We propose a sound orientation rule for causal discovery that applies under weaker assumptions.
  arXiv  Detail & Related papers  (2020-10-27T13:04:08Z)

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.