Low-Margin Branch Points in Deterministic LLM Deliberation
cs.AI
Submitted: 2026-10-31
Updated: 2026-11-09
License: http://creativecommons.org/licenses/by/4.0/
The gist: Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions.
Terminology
Abstract
Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions. Because each response becomes context for later agents, a changed greedy token can redirect a transcript-mediated execution. We present a white-box audit of this local failure mode in a five-agent committee under greedy decoding. We prospectively select low- and high-margin token positions, require exact no-op re- play, inject norm-relative residual displacements, and measure first transcript divergence within ten generated tokens. Low- margin positions are more branch-sensitive than high-margin controls, while matched margin-reducing gradient directions branch substantially more often than margin-increasing con- trols. We then continue selected realized branches through the committee to distinguish textual persistence from preference and final-decision changes. The contribution is a controlled audit for local branch susceptibility in this specified protocol, not an estimate of deployment frequency, decision correct- ness, or a phenomenon unique to multi-agent systems.
Sources
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
- Towards Automated Circuit Discovery for Mechanistic Interpretability
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Qwen2.5 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents