cs.AINov 3, 2026

ATC: Agent Trajectory Control for Role-Contract Enforcement in Black-Box Multi-Agent Systems

Authors: Maisha Maliha, Vishal Pramanik, Sumit Kumar Jha

Organizations: University of Oklahoma · University of Florida

Abstract

Multi-agent LLM systems assign different responsibilities to different agents: one plans, another retrieves evidence, another verifies, another executes. This division of labor is only meaningful if each agent stays within the functions it is authorized to perform. Over many turns, however, an agent can produce a locally reasonable message that exercises authority belonging to another role: a verifier that begins planning, a retriever that asserts unsupported conclusions, an executor that changes state no one approved. We formalize this as role drift, a turn-level breach of an agent's role contract. We introduce Agent Trajectory Control (ATC), which makes each role's authority explicit as a contract and enforces it at the point where a message would enter the shared conversation. ATC scores a proposed output for out-of-role deviation, leakage into the functions of other roles, impermissible speech acts, and logical contract breaches, then computes a leakage-regularized target that constrains regeneration; the revised message is re-checked before admission. Enforcement acts on the message rather than the generator, so ATC governs agents whose internal representations are unavailable. Across homogeneous and heterogeneous teams, ATC improves task performance and role consistency while lowering role-drift energy relative to strong baselines spanning prompting, memory, workflow control, and activation editing, with the largest gains under explicit role-confusion stress tests and in larger, more diverse teams.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models

    Aug 12, 2026Zhou Liu, Chaoyang Han, Zewei Pan +2LLM Agent TrainingMulti-Agent LLMs

  2. Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity

    Apr 3, 2026Guoling Zhou, Wenpei Han, Fengqin Yang +3Behavioral Consistency of LLM AgentsLLM Agents

  3. Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning

    May 27, 2026Ling-Yue Ge, Lan-Zhe GuoMulti-Agent LLM SystemsLLM Agent Orchestration