Benchmarking

TL;DR: Legal zero‑days are previously unnoticed faults in how laws interlock. When triggered, they can invalidate decisions, stall regulators, or nullify safeguards immediately—no lawsuit required. A new evaluation finds current AI models only occasionally detect such flaws, but the capability is measurable and likely to grow. Leaders should treat statutory integrity like cybersecurity: threat model, red‑team, patch. What’s a “legal zero‑day”? Think of a software zero‑day, but in law. It’s not a vague “loophole,” nor normal jurisprudential drift. It’s a precise, latent defect in how definitions, scope clauses, or cross‑references interact such that real‑world effects fire at once when someone notices—e.g., eligibility rules void an officeholder, or a definitional tweak quietly de‑scopes entire compliance obligations. ...

TL;DR PacifAIst stress‑tests a model’s behavioral alignment when its instrumental goals (self‑preservation, resources, or task completion) conflict with human safety. In 700 text scenarios across three sub‑domains (EP1 self‑preservation vs. human safety, EP2 resource conflict, EP3 goal preservation vs. evasion), leading LLMs show meaningful spread in a “Pacifism Score” (P‑Score) and refusal behavior. Translation for buyers: model choice, policies, and guardrails should not assume identical safety under conflict—they aren’t. Why this matters now Most safety work measures what models say (toxicity, misinformation). PacifAIst measures what they would do when a safe choice may require self‑sacrifice—e.g., dumping power through their own servers to prevent a human‑harmful explosion. That’s closer to agent operations (automation, tool use, and control loops) than classic content benchmarks. If you’re piloting computer‑use agents or workflow copilots with action rights, this is the missing piece in your risk model. ...

When language models battle, their strategies talk back. In a controlled Pokémon tournament, eight LLMs drafted teams, chose moves, and logged natural‑language rationales every turn. Beyond win–loss records, those explanations exposed how models reason about uncertainty, risk, and resource management—exactly the traits we want in enterprise decision agents. Why Pokémon is a serious benchmark (yes, really) Pokémon delivers the trifecta we rarely get in classic AI games: Structured complexity: 18 interacting types, clear multipliers, and crisp rules. Uncertainty that matters: imperfect information, status effects, and accuracy trade‑offs. Resource management: limited switches, finite HP, role specialization. Crucially, the action space is compact enough for language-first agents to reason step‑by‑step without search trees—so we can see the strategy, not just the score. ...

Financial AI promises speed and scale — but in finance, a single misplaced digit can be the difference between compliance and catastrophe. The FAITH (Framework for Assessing Intrinsic Tabular Hallucinations) benchmark tackles this risk head‑on, probing how well large language models can faithfully extract and compute numbers from the dense, interconnected tables in 10‑K filings. From Idea to Dataset: Masking With a Purpose FAITH reframes hallucination detection as a context‑aware masked span prediction task. It takes real S&P 500 annual reports, hides specific numeric spans, and asks the model to recover them — but only after ensuring three non‑negotiable conditions: ...

In the age of Transformers and neural nets that write poetry, it’s tempting to assume deep learning dominates every corner of AI. But in quantitative investing, the roots tell a different story. A recent paper—QuantBench: Benchmarking AI Methods for Quantitative Investment1—delivers a grounded reminder: tree-based models still outperform deep learning (DL) methods across key financial prediction tasks. ...

When large language models (LLMs) learned to think step-by-step, the world took notice. Chain-of-Thought (CoT) reasoning breathed new life into multi-step arithmetic, logic, and even moral decision-making. But as multimodal AI evolved, researchers tried to bring this paradigm into the visual world — by editing images step-by-step instead of all at once. And it failed. In the recent benchmark study Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark1, the authors show that CoT-style image editing — what they call sequential editing — not only fails to improve results, but often worsens them. Compared to applying a single, complex instruction all at once, breaking it into sub-instructions causes notable drops in instruction-following, identity preservation, and perceptual quality. ...

In the high-stakes world of business process automation (BPA), it’s not enough for AI agents to just complete tasks—they need to complete them correctly, consistently, and transparently. At Cognaptus, we believe in treating automation with the same scrutiny you’d expect from a court of law. That’s why we’re introducing CognaptusJudge, our novel framework for evaluating business automation, inspired by cutting-edge research in LLM-powered web agents. ⚖️ Inspired by Online-Mind2Web Earlier this year, a research team from OSU and UC Berkeley published a benchmark titled An Illusion of Progress? Assessing the Current State of Web Agents (arXiv:2504.01382). Their findings? Many agents previously hailed as top performers were failing nearly 70% of tasks when evaluated under more realistic, human-aligned conditions. ...