Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper

arXiv:2610.11542 · cs.CL, cs.AI · Submitted 2026-10-08 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-08

Updated: 2026-10-13

Comments: 29 pages, 3 figures. v3: corrects a statement about the companion paper (Section 6). v2 added the code and data repository and its licence (Appendix F) and described the released May 2026 logs as excerpts. Changes are listed at the end of Appendix F; no result changed. Code, logs and analysis: https://github.com/0x-AO-Protocol/constitutional-gating-testbed. Companion paper: arXiv:2610.09772

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Frustration — 15× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Cognitive Load — 3× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 3× in this paper
• LLM judge — 3× in this paper · explained in 2 episodes
• Steering — 3× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 1× in this paper
• In-Context Learning — 1× in this paper · explained in 7 episodes
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Why Do Multi-Agent LLM Systems Fail?
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• The Llama 3 Herd of Models
• Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
• LLMs Get Lost In Multi-Turn Conversation
• Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
• Ignore Previous Prompt: Attack Techniques For Language Models
• Efficient Guided Generation for Large Language Models
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering