arXiv AI
Aug 11
Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol
arXiv:2608. 08882v1 Announce Type: cross Abstract: AI tools that help people judge online claims are usually evaluated while the tool is present.
Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol
AI tools that help people judge online claims are usually evaluated while the tool is present. This paper asks a different question: after using such a tool, what can the user still do on their own?
Related stories
arXiv Machine Learning
Jul 1
The Calibration Turn in AI-Assisted Research: A Conceptual and Methodological Framework for Evidence-Licensed Claims
arXiv:2606. 31273v1 Announce Type: new Abstract: AI-assisted research has entered a stage in which the central question is not only whether systems can generate hypotheses, run experiments, or produce manuscripts, but whether their scientific claims are calibrated to the evidence that supports them.
arXiv Machine Learning
Jul 30
When benchmark inferences do not compose: Projectibility in AI evaluation
arXiv:2607. 26159v1 Announce Type: cross Abstract: An AI benchmark result rarely reaches a consequential claim in one step.
arXiv AI
Jun 10
Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm
arXiv:2605. 27914v2 Announce Type: replace-cross Abstract: Benchmarking is mature where answers are verifiable -- math, code, reasoning -- but the fastest-growing uses of LLMs are subjective and human-facing: companionship, emotional support, counseling.
arXiv AI
Aug 11
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
arXiv:2608. 05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.
arXiv AI
2d ago
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
arXiv:2608. 13706v1 Announce Type: cross Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text.
arXiv AI
Jul 24
pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development
arXiv:2607. 21268v1 Announce Type: cross Abstract: In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists.
arXiv AI
Jun 4
From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents
arXiv:2606. 04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, environments, and other agents.
arXiv AI
Jun 9
AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation
arXiv:2606. 09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds.
arXiv AI
Jul 22
Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent
arXiv:2607. 18257v1 Announce Type: cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate.
arXiv Machine Learning
Aug 3
The Checking Problem: What must be true before AI ships in a regulated firm
arXiv:2607. 28666v1 Announce Type: cross Abstract: Enterprise AI programmes stall at a rate that is widely quoted and poorly explained.
arXiv AI
Jun 2
Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis
arXiv:2606. 00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error.