arXiv AI
Jul 13
Ceci n'est pas une pipe: AI systems as semantic abstractions
arXiv:2607. 09489v1 Announce Type: new Abstract: An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation.
Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents
Related stories
arXiv AI
Aug 3
Beyond Component Testing: Validating Agentic AI Systems
arXiv:2607. 29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation.
arXiv AI
Aug 13
Agent Safety Should Be a Runtime Contract
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv AI
Aug 7
Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflows
arXiv:2608. 05602v1 Announce Type: new Abstract: Generative AI systems are increasingly deployed in high-stakes professional contexts, where their outputs shape what users believe, how they reason, and what they treat as settled.
arXiv AI
4d ago
VeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate actio...
arXiv AI
Jul 9
Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
Hugging Face Trending Papers
Sep 21
Beyond Natural Language: An Agent-Native Language for Autonomous Science
As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relies on natural-language prose: a...
Hugging Face Trending Papers
Jul 28
Position: Evaluation Scores Are Perishable Knowledge Claims
Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation.
arXiv AI
2d ago
Cybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic Delegation
The paper argues that as AI systems increasingly generate code, the bottleneck has shifted to supervising these systems, revealing a vocabulary gap between cybernetic coordination (actions aligning with the world) and epistemic coordination (understanding that can be verified). It critiques current oversight that merely approves outputs, proposing instead that every consequential choice by an agent must include a retrievable condition explaining why it was made, enabling third‑party verification. The authors illustrate this with three delegation episodes, introduce a two‑part reconstruction test, and propose the ORRCF convention to embed such conditions in all recorded decisions.
arXiv Machine Learning
Jul 30
Position: Evaluation Scores Are Perishable Knowledge Claims
arXiv:2607. 26191v1 Announce Type: cross Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results.
arXiv AI
Aug 18
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
arXiv:2608. 14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools.
arXiv AI
Aug 24
No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.