# Coordination Requires Simplification: Thermodynamic Bounds on Multi-Objective Compromise in Natural and Artificial Intelligence

arXiv: https://arxiv.org/abs/2509.23144 · HTML: https://mlsanity.com/paper/2509.23144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 65 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [A Voting-Based System for Ethical Decision Making](https://mlsanity.com/paper/1709.06692/) (2017)
- [A World unto Itself: Human Communication as Active Inference](https://mlsanity.com/paper/1906.10538/) (2019)
- [The Implications of the No-Free-Lunch Theorems for Meta-induction](https://mlsanity.com/paper/2103.11956/) (2021)
- [Collective dynamics of belief evolution under cognitive coherence and social conformity](https://mlsanity.com/paper/1509.01502/) (2015)
- [Consensus between Epistemic Agents is Difficult](https://mlsanity.com/paper/2201.04642/) (2022)

## Abstract (arXiv)

Information-processing systems that coordinate multiple agents and objectives face fundamental thermodynamic constraints. We show that solutions with maximum utility to act as coordination focal points have a much higher selection pressure for being findable across agents rather than accuracy. We derive that the information-theoretic minimum description length of coordination protocols to precision varepsilon scales as L(P)≥ NKlog2 K+N2d2log (1/varepsilon) for N agents with d potentially conflicting objectives and internal model complexity K. This scaling forces progressive simplification, with coordination dynamics changing the environment itself and shifting optimization across hierarchical levels. Moving from established focal points requires re-coordination, creating persistent metastable states and hysteresis until significant environmental shifts trigger phase transitions through spontaneous symmetry breaking. We operationally define coordination temperature to predict critical phenomena and estimate coordination work costs, identifying measurable signatures across systems from neural networks to restaurant bills to bureaucracies. Extending the topological version of Arrow's theorem on the impossibility of consistent preference aggregation, we find it recursively binds whenever preferences are combined. This potentially explains the indefinite cycling in multi-objective gradient descent and alignment faking in Large Language Models trained with reinforcement learning with human feedback. We term this framework Thermodynamic Coordination Theory (TCT), which demonstrates that coordination requires radical information loss.