Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents
Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic probability axioms even when every component is locally coherent. We formalise this locally coherent, globally incoherent failure via the compositional residual eps*, the L2 distance from the composed quote to the joint coherent polytope, computable at runtime from system output and the declared cross-component coupling constraints. A product-structure dichotomy characterises when local coherence suffices, and a Rayleigh-quotient prediction matches the observed residual within 7% on three of four relation classes. A hierarchical Boyle-Dykstra projection repairs the composition deterministically; an anytime-valid e-process gives sequential coherence monitoring. Across 1,876 ensemble cliques on a four-LLM mid-tier panel (frontier-panel rerun in Section 5.5), eps* > 0 on 33-94% of cliques, translating to +0.115 nats per bet of regret on 1,770 resolved bets under the proportional allocation rule (the gain collapses to +0.006 under bettors that themselves coherentise). Three intuitive LLM-side mitigations(retrieval, partition-aware prompting, aggregator-LLM) each fail or regress.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Refining Compositional Diffusion for Reliable Long-Horizon Planning
Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score composition. However, when local plan distributions are multimodal, existing com…
Compositional Diffusion with Guided Search for Long-Horizon Planning
Generative models have emerged as powerful tools for planning, with compositional approaches offering particular promise for modeling long-horizon task distributions by composing together local, modular generative models…
Robot ManipulationVideo Generation3D PixBrush: Image-Guided Local Texture Synthesis
We present 3D PixBrush, a method for performing image-driven edits of local regions on 3D meshes. 3D PixBrush predicts a localization mask and a synthesized texture that faithfully portray the object in the reference ima…
Compositional 3D Scene Generation using Locally Conditioned Diffusion
Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited…
Scene GenerationText to 3DSomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally. We evaluate four open-weight instruction-tuned models on Soma…