Counterfactual Graph for Multi-Agent LLM Calibration

• URL: http://arxiv.org/abs/2605.30653v1
• Date: Thu, 28 May 2026 23:16:29 GMT
• Title: Counterfactual Graph for Multi-Agent LLM Calibration
• Abstract summary: 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.
• Score: 35.92917436685906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable. We show that this assumption can fail after agents communicate. 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. We propose CAGE-CAL, a counterfactual agent-graph calibration framework for multi-agent LLMs. For each query, CAGE-CAL compares an observed post-communication agent graph with a matched counterfactual no-communication graph, capturing both pairwise failure correlations and group-level dependencies. Rather than simply counting how many agents agree, CAGE-CAL estimates the counterfactual shift between observed and no-communication dependence, and calibrates confidence accordingly. Across five benchmarks, CAGE-CAL improves reliability discrimination with competitive ECE, and its calibrated confidence further improves topology selection over the best fixed-topology strategy.

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)
• Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems [13.096154493399764]
  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.
  arXiv  Detail & Related papers  (2026-08-04T07:11:28Z)
• Multiagent Protocols with Aggregated Confidence Signals [7.128020779227392]
  Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP)<n>Prior work uses confidence within multiagent debate (MAD) to weight messages, trigger debate, or calibrate individual agents, but it never aggregates these into a single confidence for the system itself.<n>We introduce three protocols that produce a final answer along with a single aggregated confidence by first transforming raw confidence signals to make them comparable across models, then combining them via soft voting or a probability fusion.
  arXiv  Detail & Related papers  (2026-06-11T17:12:11Z)
• DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs [8.797488068424181]
  We propose a controlled-communication coordination framework named DarkForest.<n>DarkForest keeps agents independent, so each agent produces an answer without seeing the others' outputs.<n>Experiments show that DarkForest achieves leading overall quality, improves the strongest baseline by up to 30.7% on benchmark metrics, and reduces token consumption by up to $6.5times$ compared with communication-heavy baselines.
  arXiv  Detail & Related papers  (2026-05-24T17:34:27Z)
• Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling [22.248543228906115]
  LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities.<n>We introduce SIGMA, a novel SIgned Graph-informed Multi-Agent reasoning framework.<n>We show that SIGMA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-19T06:11:11Z)
• FERA: Uncertainty-Aware Federated Reasoning for Large Language Models [60.52562148874846]
  We study federated reasoning, where a server improves multi-step reasoning by coordinating with heterogeneous clients holding private demonstrations.<n>The key challenge is that client reliability is query-dependent, while the server cannot inspect client data to determine which contributions are trustworthy.<n>We propose Uncertainty-Aware Federated Reasoning (FERA), a training-free framework based on iterative server-client co-refinement.
  arXiv  Detail & Related papers  (2026-05-11T07:04:51Z)
• Robust Multi-Agent LLMs under Byzantine Faults [12.778788735297288]
  Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability.<n> unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance.<n>Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation.
  arXiv  Detail & Related papers  (2026-05-09T17:37:43Z)
• Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning [68.85408801740228]
  We propose textbfAgent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning problem.<n>Our method learns decentralized communication decisions using Qmix value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph.<n>Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
  arXiv  Detail & Related papers  (2026-04-01T00:38:24Z)
• Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation [0.7418138958218443]
  Intraclass Correlation Coefficient (ICC) is a metric from measurement science to characterize variance.<n>ICC decomposes observed variance into between-Query variance (task difficulty) and within-Query variance (agent inconsistency)<n>We demonstrate that ICC converges by n=8-16 trials for structured tasks and n>=32 for complex reasoning, enabling practitioners to set evidence-based resampling budgets.
  arXiv  Detail & Related papers  (2025-12-07T07:58:13Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth [0.0]
  We introduce a new approach in which several advanced large language models produce and answer intricate, doctoral-level probability problems.<n>Our investigation focuses on how agreement among diverse models can signal the reliability of their outputs.
  arXiv  Detail & Related papers  (2025-02-28T06:20:52Z)
• DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics [52.242449026151846]
  Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs)<n>We propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence.
  arXiv  Detail & Related papers  (2024-07-08T22:15:01Z)

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.