Very excited to share that our paper "Towards a Science of AI Agent Reliability" was accepted at ICML 2026! See you in Seoul! 🎉 We just released our camera ready version with three important updates (details below). We also recorded a short video on the paper's contributions. Main changes (full discussion at hal.cs.princeton.edu/reliabi…): 1️⃣We have added the latest set of frontier models to our evaluation (GPT 5.5, Gemini 3.1 Pro and 3.5 Flash, and Claude Opus 4.7) and find that they are not meaningfully more reliable than previously released models. Agent reliability is still far from being solved. 2️⃣We have updated the definition and measurement of our outcome consistency metric, which contained a typo in the pre-print we initially released. This caused us to under-estimate outcome consistency in our initial set of results. We have updated the paper and our codebase to the corrected metric. Despite this change, our new results show that outcome consistency is still surprisingly low across many reported models. 3️⃣We discovered multiple issues in our HAL Generalist Agent scaffold that we used for our experiments on GAIA. Notably, we discovered multiple instances of answer leakage and agents cheating on our evaluation. This caused us to slightly over-estimate both accuracy and reliability. At the same time, we noticed that the scaffold was overly constrained in terms of permissible software library imports. This caused us to slightly under-estimate both accuracy and reliability. We have done a rigorous audit of the scaffold and have fixed those issues. Overall, we saw that our resulting accuracy and reliability numbers are not meaningfully impacted by this change when compared to our original numbers. 📄Our paper: arxiv.org/abs/2602.16666 📊Our dashboard: hal.cs.princeton.edu/reliabi… 🎥Short video: youtu.be/qftDfEft7U0 Joint work w/ @sayashk, @PKirgis, @khl53182440, @SaitejaUtpala, and @random_walker.

First paper of my PhD with my amazing advisors! There’s been a ton of hype and media coverage on OpenEvidence as an “AI co-pilot for clinicians”… and our long-horizon benchmark puts them to the test!! Our results suggest they are far from reliable for downstream use.

At last week's developer conference, Google claimed that their newest frontier model produced an operating system from just a single prompt and ~$900 in API cost. At first sight, this seems impressive. But on closer look, the evidence is much thinner than the headline suggests. Most notably: - The "single prompt" framing suggests that the agent could do this from just a few sentences with high-level instructions. But the prompt itself is many thousands of lines long and it is unclear what instructions Google provided in the prompt (and how much effort it took to even come up with the prompt in the first place). - There is a lot of OS code on the internet and it is often attempted as a class project in college OS classes. Based on the information provided in Google's blog post, it is unclear to what extent the agent simply copied a well-known implementation from the internet. - In such long-running, complex implementation tasks, it is important to understand what degree of human intervention was performed to help the agent achieve its goals. However, Google remains ambiguous about the level of hand-holding they performed in this experiment. They say that "no additional guidance or corrections from a human" were necessary, yet they document instances of imposing anti-cheating mechanisms between runs. - Many key artifacts, such as the code, the prompt, and agent logs are unreleased. This makes it impossible for external researchers to verify these marketing claims. - To Google's credit, they did release the overall cost and token budget. These details often remain undisclosed, and sharing them is a first step in the right direction. More detail in our writeup at normaltech.ai/p/did-googles-… w/ @sayashk @RishiBommasani Andrew Schwartz @random_walker

Working with agents for the past months has me convinced that outcome-only evaluation is a flawed approach to benchmarking. You need to look at the logs to understand if the agent really did its job! In our paper Log analysis is necessary for credible evaluation of AI agents, we ➡️introduce a taxonomy of threats to credible evaluation of AI agents (including construct validity and safety evaluation concerns); ➡️outline four key principles for conducting log analysis effectively; ➡️present a case study of how log analysis helped us to find a variety of benchmarking errors on τ-bench; and ➡️give a set of recommendations to improve log analysis quality and adoption. 📄arxiv.org/abs/2605.08545 More details in @PKirgis's thread below ⬇️

Most agentic benchmarks center around tasks that are automatically verifiable. But any task that is veriafiable is also easy to optimize for. This work instead describes the future of critical open world evaluations. Led by @sayashk, our current draft is now live.

Glad to be a part of this initiative to develop open-world evaluations for AI. We need the ability to assess just how capable agents are becoming in order to anticipate and respond to the impact they can have on real world systems and transactions. An agent that can successfully act on the general instruction “build an app and get it posted in the App Store” is one that brings us closer to an economy of agents, with significant implications for how markets behave and need regulating arxiv.org/pdf/2509.01063

Yesterday, we announced CRUX, a project that aims to conduct regular “open-world evaluations,” where we will be testing the ability of AI agents to complete long-horizon tasks in messy, real-world environments. @sayashk's post dives into the details; here are a few of my own thoughts about why this is worth doing.

This paper makes a strong case for open-world evaluations as a complement to traditional benchmarks, particularly for realistic, long-horizon, open-ended settings! Glad the AISI SoE team could contribute to this effort.

Benchmarks are saturated more quickly than ever. How should frontier AI evaluations evolve? In a new paper, we argue that the AI community is already converging on an answer: Open-world evaluations. They are long, messy, real-world tasks that would be impractical for benchmarks.