arXiv:2611.13487v1 Announce Type: new Abstract: Existing Chinese educational corpora often suffer from fragmented coverage and a lack of systematic…
Category: AI
The Web Is More Than Enough, by Paul Ford
My comment on The Web Is More Than Enough, by Paul Ford — Hacker News. OK, this comment convinced me to give that a shot. Here’s a thing I made in…
When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference
arXiv:2611.13456v1 Announce Type: new Abstract: As AI-based products permeate society, specifically systems using generative models, a belief system is…
SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering
arXiv:2611.13410v1 Announce Type: new Abstract: Low-bit quantization reduces the inference cost of LLM agents but can compromise task success. Examining…
No finite rulebook can certify every safe program: an impossibility theorem for gatekeeping AI agents
arXiv:2611.13367v1 Announce Type: new Abstract: An AI assistant writes small programs, and a gatekeeper must decide, from the code alone, whether each one…
Living constitutions: Participatory alignment for sovereign foundation models
arXiv:2611.13402v1 Announce Type: new Abstract: In Constitutional AI, a plain-text “constitution” encodes values and gets incorporated into a model via…
SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning
arXiv:2611.13454v1 Announce Type: new Abstract: We introduce SafeRoute-MAS, a coverage-aware, risk-calibrated procedure that keeps all specialist messages…
NTT’s Physics-Based World Model Screens Robot Actions Before Execution
On November 11, 2026, NTT, Inc. announced a physics-based world model that evaluates candidate robot actions before execution to reduce failures such as…
Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting
arXiv:2611.13388v1 Announce Type: new Abstract: We present a neuro-symbolic framework that pairs online-adaptive Fuzzy Cognitive Maps (FCMs) with long…
Veritas: A Verifier Generation Harness for Agent Tasks
arXiv:2611.13336v1 Announce Type: new Abstract: The effectiveness of a self-improving system relies heavily on the quality of its verifier, which judges…