Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems

• URL: http://arxiv.org/abs/2608.03239v1
• Date: Tue, 04 Aug 2026 07:11:28 GMT
• Title: Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
• Abstract summary: We study the effects of making inter-agent relation semantics explicit in large language model-based multi-agent systems.<n>We find that increasing relational positivity tends to make agents coordinate or agree more readily.<n>We argue that relational priors should not be a default add-on for LLM-MAS.
• Score: 13.096154493399764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit social expectations: agents may be expected to trust, challenge, defer to, or collaborate with peers. We study the effects of making inter-agent relation semantics explicit. We use a minimal signed-network formulation of relational priors and inject natural-language renderings into agent system prompts while holding the task protocol fixed. Across a commons-governance simulation and multi-agent debate, relational priors primarily act as convergence pressure: increasing relational positivity tends to make agents coordinate or agree more readily. This pressure can help when utility rewards behavioral alignment, as in sustainable resource governance and subjective consensus. It does not, however, reliably improve accuracy. In objective QA debates, higher positivity can increase agreement even when correctness-conditioned agreement does not improve and may decline in some settings. Effects vary by model backbone, relation type, and topology; explicit neutrality is not equivalent to omitting relational framing. We argue that relational priors should not be a default add-on for LLM-MAS. Their safer use is diagnostic and task-specific: compare against a no-prior baseline, monitor correctness-conditioned metrics when truth matters, and omit the relational layer when validation does not justify it.

Related papers

• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation [79.43842208099619]
  Source-free domain adaptation (SFDA) adapts a source-trained model to an unlabeled target domain without source data.<n>We formulate VLM-guided SFDA as a sample-wise reliability-allocation problem.<n>We propose Consensus-Driven Shift Modulation (COSMO) to replace expert-to-expert guidance with co-adaptation.
  arXiv  Detail & Related papers  (2026-08-05T09:10:30Z)
• From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents [56.187590188698955]
  Large Language Models have enabled increasingly capable autonomous agents, yet personalization remains critical for making such agents practically useful.<n>Recent benchmarks have begun evaluating personalization in agents, but they largely rely on static preference snapshots, fixed interaction logs, or question answering over predefined user profiles.<n>We introduce IBA-Bench, a benchmark for implicit behavioral alignment constructed from longitudinal interaction histories.<n>We propose IBA-Agent, an agent framework that reconciles conflicting priorities through broad retrieval and trajectory-level alignment.
  arXiv  Detail & Related papers  (2026-08-03T12:52:04Z)
• Counterfactual Graph for Multi-Agent LLM Calibration [35.92917436685906]
  Communication can induce correlated failures and false consensus, so the same vote share may reflect reliable agreement in one topology but over-confidence in another.<n>We propose CAGE-CAL, a counterfactual agent-graph calibration framework for multi-agent LLMs.
  arXiv  Detail & Related papers  (2026-05-28T23:16:29Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Can AI Agents Agree? [32.75269650141292]
  Large language models are increasingly deployed as cooperating agents, yet their behavior in adversarial consensus settings has not been studied.<n>We evaluate LLM-based agents on a Byzantine consensus game over scalar values using a synchronous all-to-all simulation.<n>We find that valid agreement is not reliable even in benign settings and degrades as group size grows.
  arXiv  Detail & Related papers  (2026-03-01T18:18:59Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• Verifiable Semantics for Agent-to-Agent Communication [0.2866560512724962]
  Multiagent AI systems require consistent communication.<n>Natural language is interpretable but vulnerable to semantic drift.<n>We propose a certification protocol based on the stimulus-meaning model.
  arXiv  Detail & Related papers  (2026-02-18T12:55:58Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning [41.461840578204956]
  Large Language Model (LLM)-based agents learn new tasks without catastrophic forgetting.<n>Agent-Dice is a parameter fusion framework based on directional consensus evaluation.<n>Experiments on GUI agents and tool-use agent domains demonstrate that Agent-Dice exhibits outstanding continual learning performance.
  arXiv  Detail & Related papers  (2026-01-07T06:43:50Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary [65.268245109828]
  Non-human-like behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon is the generation of inconsistent predictions, which produces contradictory results. We propose a practical approach that alleviates the inconsistent behaviour issue by improving PLM awareness.
  arXiv  Detail & Related papers  (2023-10-24T06:15:15Z)

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.