English
Related papers

Related papers: Structural Rigidity and the 57-Token Predictive Wi…

200 papers

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…

Artificial Intelligence · Computer Science 2026-03-24 Gregory M. Ruddell

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…

Artificial Intelligence · Computer Science 2026-05-27 Alan L. McCann

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,…

Computation and Language · Computer Science 2026-05-13 Pruthvinath Jeripity Venkata

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…

Computation and Language · Computer Science 2026-04-09 Angelina Hintsanen

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,…

Artificial Intelligence · Computer Science 2026-05-27 Alan L. McCann

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…

Artificial Intelligence · Computer Science 2026-05-15 Rahul Kumar

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…

Software Engineering · Computer Science 2026-02-09 Karen Sargsyan

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…

Software Engineering · Computer Science 2026-04-30 Twinkll Sisodia

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…

Multiagent Systems · Computer Science 2026-03-10 Jason Starace , Terence Soule

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…

Artificial Intelligence · Computer Science 2025-11-19 Jiahao Wu , Shengwen Yu

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,…

Artificial Intelligence · Computer Science 2026-03-06 Junbo Zhao , Ting Zhang , Can Li , Wei He , Jingdong Wang , Hua Huang

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…

Artificial Intelligence · Computer Science 2026-04-23 Robert Reinertsen

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…

Artificial Intelligence · Computer Science 2026-04-24 Michael O'Herlihy , Rosa Català

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…

Artificial Intelligence · Computer Science 2026-05-27 Alan L. McCann

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…

Machine Learning · Computer Science 2026-05-29 Weicheng Xue

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…

Artificial Intelligence · Computer Science 2026-05-19 Zachary Burton

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…

Cryptography and Security · Computer Science 2026-04-07 Samar Ansari

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…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

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…

Cryptography and Security · Computer Science 2026-03-23 Ziling Zhou

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…

Artificial Intelligence · Computer Science 2026-04-14 Seulki Lee
‹ Prev 1 2 3 10 Next ›