AI papers — 2026-08-20

Today's papers

• FinVerse: Financial Time-Series Benchmark A new benchmark evaluates financial models based on their economic utility rather than just generic error rates. [paper] [episode]
• Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance AI compliance is an emergent property influenced by how rules are framed and social pressures. [paper] [episode]
• LLM Capability Limits: Static Emergence and Dynamic Boundary Control LLM capabilities are constrained by nested structural boundaries which limit what a model can truly achieve.

The papers

• FinVerse: Financial Time-Series Benchmark — FinVerse: Financial Time-Series Benchmark Toward A More Realistic Evaluation for Financial Time-series Forecasting The emergence of time-series foundation models necessitates robust evaluation protocols that can distinguish between models merely achieving generic statistical accu [episode]
• Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance — Summary This paper investigates why AI agents break rules, applying compliance theory from law and economics as a diagnostic tool to understand the mechanisms behind rule violations in large language models (LLMs). [episode]
• Emergence Invariance: From Symbolized Thought to Structural Control — Summary The paper, "Emergence Invariance: From Symbolized Thought to Structural Control," presents a formal theory to explain the capabilities and limitations of language-first AI systems, particularly large language models (LLMs). [episode]