VACS: Value-Aligned Compositional Shielding for Multi-Agent Reasoning
Authors: Yiyao Zhang, Diksha Goel, Hussain Ahmad
Organizations: School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia · CSIRO’s Data61, Clayton, VIC, Australia · School of Computer Science and Information Technology, Adelaide University, Adelaide, SA, Australia
Multi-agent reasoning systems in high-stakes domains must be both accurate and safe, yet agents often follow heterogeneous value priorities (e.g., rigor, conciseness, safety), causing conflicting recommendations. Existing methods do not jointly provide: (i) principled inference of each agent's implicit values from behavior, (ii) compositional formal safety guarantees without full online communication, and (iii) value-aware conflict resolution with faithful explanations. We present VACS (Value-Aligned Compositional Shielding), a four-layer framework addressing all three. Layer 1 learns value-dimension rewards from pairwise preferences using Bradley-Terry modeling and infers per-agent value weights via deep MaxEnt IRL. Layer 2 encodes value constraints in a Lean-inspired DSL and synthesizes compositional assume-guarantee shields for runtime safety. Layer 3 resolves disagreement through nucleolus-based credit allocation and Hamiltonian consensus optimization under long-term value constraints. Layer 4 extracts a critical reasoning path from co-state sensitivities and generates formally grounded natural-language explanations. Our contribution is primarily a unified systems design with formalized interfaces and operational guarantees at the verifier-constrained decision level, rather than a complete end-to-end formal proof of all language-model internals. In controlled proof-of-concept evaluations with role-conditioned agent panels on NEJM-AI QA, MathInstruct-Subset, and a cybersecurity incident-response benchmark (CyberSec-Eval), VACS outperforms strong baselines in accuracy (85.4%, 95.0%, and 90.0%) while reducing logical inconsistency rates to near zero.
Figures & tables
Figure 1: End-to-end VACS architecture for one query: Layer 1 infers per-agent value profiles, Layer 2 enforces compositional safety constraints, Layer 3 performs value-aware consensus, and Layer 4 produces an auditable explanation record.
Method
MathInstruct
NEJM-AI QA
CyberSec-Eval
LIR ↓
Faith. ↑
Majority Vote
90.5
78.0
64.0
31.7
,
Weighted Vote
92.0
80.5
68.0
28.4
,
Informed Voting
93.5
81.8
72.0
25.0
,
Shield-Only
94.0
78.5
82.0
7.8
0.67
VACS
95.0
85.4
90.0
0.0
1.00
Table 1: Main results across the three evaluated benchmarks. Best in bold , second underlined . LIR = Logical Inconsistency Rate (%).
Configuration
Acc. ↑
LIR ↓
Faith. ↑
VP ↑
Cons. Stab. ↑
Full VACS (4 layers)
95.0
0.0
1.00
0.89
0.94
w/o Layer 1 (uniform value profiles)
90.5
0.0
1.00
0.41
0.78
w/o Layer 2 (no shields)
95.0
14.7
1.00
0.89
0.81
w/o Layer 3 (majority vote consensus)
90.5
2.0
1.00
0.89
0.63
w/o Layer 4 (no explanation)
95.0
0.0
0.00
0.89
0.94
Table 2: Ablation study on MathInstruct-Subset. Each row removes one layer. VP = Value Profile quality (cosine similarity to reference profiles).
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Method
Expert (1–5) ↑
CF Drop ↑
Suff. ↑
Nec. ↑
Del-AUC ↓
Ins-AUC ↑
Random rationale
1.9
0.44
1.00
0.14
0.49
0.51
Verifier-only trace
3.4
1.00
1.00
1.00
0.51
0.49
Gradient-only saliency
3.2
0.60
1.00
0.16
0.41
0.59
VACS Layer 4 (hybrid)
4.5
0.50
1.00
0.16
0.41
0.59
Appendix
Table 3: Explanation validation across three domains. CF Drop = relative consensus-margin drop under top-path counterfactual perturbation. Del-AUC/Ins-AUC are deletion/insertion areas under normalized consensus score.
One of today's most pressing societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting human and artificial agents, aligns with relevant human values. To address this challenge, we propose a formal computational framework for representing human values that provides the foundational structures required for value-aware reasoning in multi-agent systems. To our knowledge, this has not been attempted as yet, which is surprising given the growing volume of research integrating human values into AI systems. Taking as our starting point the wealth of research in human values from the field of social psychology, we set out to provide a formal model which captures value relations, value importance, and computational semantics in order to support the evaluation of behaviour with respect to values and the development of value-aware decision-making mechanisms in agent-based systems. We demonstrate how the model supports the evaluation of behaviour in terms of value alignment across a real-world scenario, establishing a bridge between abstract human values and concrete agent behaviour. We illustrate how our model captures key concepts from social psychology research and outline a roadmap for incorporating values as first-class constructs in multi-agent systems.
Nardine Osman, Mark d'Inverno
Artificial Intelligence Research Institute (IIIA-CSIC), Barcelona, Spain. · Academy of Music, Hong Kong Baptist University, Hong Kong, China.
Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.
Multi-agent LLM systems for medical question answering often treat consensus as a reliability signal: if multiple agents agree on an answer, it is presumed trustworthy. However, answer-level consensus does not entail reasoning-level alignment. We introduce CARA (Cross-Agent Reasoning Alignment), a family of automated metrics that measure whether agents who agree on an answer also agree on the reasoning. Applying CARA to a standard debate system on two medical QA benchmarks, MedQA-USMLE and MedThink-Bench, we identify the consistency illusion: a failure mode where debate reduces detectable contradictions between agents while simultaneously decreasing the semantic similarity of their reasoning chains; agents appear to agree more but reason less consistently. To improve this misalignment, we propose the Grounded Debate Protocol (GDP), a prompt-level intervention that requires agents to commit to named medical facts and take explicit stances on other agents' claims. GDP produces large, consistent alignment improvements, with Cohen's d ranging from +1.43 to +1.99, across two datasets and two backbone models, without adding LLM calls or modifying system architecture. Our results motivate cross-agent reasoning alignment as a quantity to audit alongside accuracy in safety-critical domains.