Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped. Current retry strategies treat both cases identically (try again and hope for the best), leaving human supervisors unable to tell whether a retry was warranted or whether the system should have halted instead. We introduce the Argent Signaling Protocol (ASP), a compact machine-readable header that accompanies every AI-generated response with structured quality signals: certainty (@C), grounding (@G), stochasticity (@S), and an assumption index that classifies the evidentiary basis of each claim. These signals enable a controller to distinguish repairable failures from containment failures and route each case differently. We evaluate ASP in two modes. In standalone mode, a 27-question document-grounded QA benchmark over the Array BioPharma/Ono license agreement compares baseline prompts against ASP-instrumented controller actions across three local GGUF models. On Qwen~(0.8B), ASP improves pass rate from 11.1% to 33.3% and mean term coverage from 36.7% to 65.4%; on Dobby~(8B), ASP produces 4 fail-to-pass recoveries, raising pass rate from 33.3% to 44.4%; on SmolLM3~(3B), ASP alternates between repair and containment per question. Aggregate improvement is meaningful (12/81 to 21/81 passes). In multi-agent mode, an ASP sidecar sits between a retrieval agent and a downstream decision agent; the sidecar blocks 100% of ungrounded upstream outputs from reaching the downstream agent (24/27 blocked, 0 ungrounded propagations).
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 18 references that are in the map. First posted on arXiv 14 May 2026.
Builds on
10 of 18 references.
Closest ancestors · 1
Same direction, newest first
Other references · 9
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2018Datasheets for Datasetscited by 1,371
- 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
- 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
- 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
- 2026Embedding Retrofitting: Data Engineering for better RAGcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems
- 2026Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability
- 2026Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
- 2026Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems
- 2026Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
- 2026ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures
- 2026Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems
- 2026Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents