LLM Capability Limits: Static Emergence and Dynamic Boundary Control
Test-time emergence in LLM systems has a deployment boundary: additional computation can realize decisions already supported by the deployed information--execution structure, while evidence, tools, memory, and executable semantics can change the class inherited by later computation. We formalize this boundary through inherited structural capability $\mathcal{D}_{\mathcal{J}}$ and resource-indexed finite realization $\mathcal{F}_s(\mathcal{J},M)$. At a common budget, Theorem 1 gives an exact decision representation: a successor improves every bounded-loss task exactly when its closed convex finite envelope retains the predecessor's. Terminal capability can therefore expand while same-budget capability strictly reverses. The same object yields finite-slice recovery and a workload-tail information radius for open-ended evaluation. Dynamically, Bellman value prices the successor capability class together with the finite policies it preserves. Nested realization makes every fixed extra resource increment vanish at saturation, allowing persistent positive successor value to dominate that increment. The resulting theory turns emergence into a boundary, compatibility, measurement, and control problem.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter wh…
Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots
Despite increasing scale and resolution, many biological measurements remain destructive, revealing only spatial information rather than the dynamics it encodes. By combining flexible representations with mechanistic con…
Budget-Aware Agentic Routing via Boundary-Guided Training
As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for s…
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved. Some studies contend that RLVR mainly …
Reinforcement LearningBoundary-Decoder network for inverse prediction of capacitor electrostatic analysis
Traditional electrostatic simulation are meshed-based methods which convert partial differential equations into an algebraic system of equations and their solutions are approximated through numerical methods. These metho…
DecoderDeep Learning