相关论文: Structural Rigidity and the 57-Token Predictive Wi…

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two are proved on paper with explicit…

The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers,…

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite…

We present a machine-checked formalization of structurally governed AI workflow architectures and prove that effect-level governance can be imposed without reducing internal computational expressivity. Using Interaction Trees in Rocq 8.19,…

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…

AI-Scientist systems that use large language models to automate research risk generating spurious discoveries through uncontrolled multiple testing. We present a functional architecture that enforces statistical rigor at two levels: a…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

We establish empirical bounds on behavioral inference through controlled experiments at scale: LLM-based agents assigned one of 36 behavioral profiles (9 belief systems x 4 motivations) generate over 1.5 million behavioral sequences across…

Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…

Multi-step theorem prediction is a central challenge in automated reasoning. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work,…

We present a simulation-based evaluation of the Inference Headroom Ratio (IHR), a dimensionless diagnostic quantity for characterizing inference stability in constrained decision systems. IHR formalizes the relationship between a system's…

Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multiple decisions may be logically consistent with the governing policy, and agreement…

We present an algebraic semantics for governed execution in which governance is axiomatized, compositional, and coterminous with expressibility. The framework, mechanized in 32 Rocq modules (~12,000 lines, 454 theorems, 0 admitted), is…

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and…

RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A…

The governance of frontier AI increasingly relies on controlling access to computational resources, yet the hardware-level mechanisms invoked by policy proposals remain largely unexamined from an engineering perspective. This paper bridges…

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…

Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines can be set more fundamentally -- at the level of value, evidence, and source…