The Archive

When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions. Yet those actions are the product: they fix cost and latency, decide how the system fails, and are the only auditable part of its behaviour. We make the action policy the measured object across 8 models, 6 parallel benchmarks and 41 languages (2.38M rollouts). The naive measurement fails: five confounds sit between raw trace similarity and any defensible claim, each able to flip a conclusion. Short t...

Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essenti...

Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning... Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning model for every execution step adds cost and latency. NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses… Source

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control. Existing safety mechanisms often treat the harness as a fixed deployment artifact, limiting their ability to evolve with emerging risks. Moreover, coupled functions across harness components obscure safety responsibility attribution, making localized evolution difficult. We propose Safety Harness Evolution (SHE), a framework that learns evolving safe boundaries from rollout trajectories. SHE decomposes the harnes...

Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have responded by scaling the proposer and ranking more samples with a learned judge or human reviewers. We argue that this *generate-and-rank* paradigm misses the problem of sparse feedback. Within a declared research problem, an agent follows the control loop of a greybox fuzzer: it proposes a candidate, executes it, observes feedback, and chooses what to try next. A fuzzer rarely finds a bug, but coverage makes partial progress observable on every execution. Fuzzers then use that sign...

The development of embodied Intelligent Virtual Agents (IVAs) that have cognitive capabilities in real-time interactive virtual environments remains a challenge, even with today's advancements in technology. Existing architectures are often focused on either the implementation of low-level reactive control systems that are constrained by commercial game engines, or high-level representations of reasoning models that can be difficult to implement in virtual worlds. This paper builds on that notion and proposes a modular cognitive architecture for deploying embodied IVAs. This architecture buil...

AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent work already shows that deployment rules can change collective behavior. Here we ask which parts of an AI institution produce safety and how they do it. This is the first paper from POLIS, an ongoing research programme studying algorithmic institutions for multi-agent systems. We report a frozen 5,280-episode study suite. The main pre-specified delegation experiment spans four model families; a targeted high-conflict diagnostic adds three addition...

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a sub...

GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on screenshots. The core task, GUI grounding, requires translating abstract user instructions into precise element coordinates. This task faces a persistent dual obstacle: conventional grounding models lack the semantic richness to interpret abstract instructions, while end-to-end MLLMs suffer from coordinate hallucinations caused by deficient fine-grained perception. We propose a regression-free framework where a frozen MLLM performs instructio...

AI coding agents now write a growing share of production code, and human security review does not scale at the rate code is generated. The agents in widest use are closed-weight, so a deploying team cannot read their internals. It can instead run an open-weight model as a reviewer over the agent's output. That reviewer's activations are readable. We ask whether reading those activations recovers a security signal that simply asking the same reviewer misses. We fit a single linear probe per model on a corpus of paired vulnerable-and-fixed Python functions, then test it without retraining on re...

Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience. However, the sparse and elongated morphology of neurons poses significant challenges to existing segmentation methods. These methods struggle to preserve both local details and global topology, leading to fragmented results. To address this, we propose NeuroRefiner, a multi-agent system that formalizes the human expert workflow involving iterative global observation and local editing. Specifically, NeuroRefiner comprises three collaborative agents dedicated to diagnosing topological errors, generating cor...

Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artifact, select candidates, and stop. We ask whether this task-specific procedure remains necessary when a frontier model acts as the optimizer. We introduce Open-Ended Optimization (OEO), which keeps the objective, permitted interactions, resource budget, data boundary, and evaluation fixed while allowing the optimizer to compose the improvement process online. We compare OEO with two complementary prescribed approaches: SkillOpt, a staged pipeli...

Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI... Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic work. Optimized to run across a range of NVIDIA edge, desktop, and workstation AI platforms, Muse Glimmer delivers 20K tokens/sec on a single GPU, enabling always-on agents to process data locally and execute complex… Source

LLMs are rapidly embedding themselves into daily life: drafting our emails, managing our schedules, and making decisions on our behalf. As they move from individual tools to participants in multi-agent organizations, an important question arises: do they reproduce the governance failures like free-riding, corruption, and entrenched leadership that plague human institutions? We introduce the Hierarchical Game (HG), a public goods game extended with managerial authority, democratic elections, and private communication. Testing six frontier models across twelve experiments that add institutions ...

External natural-language skills provide large language model (LLM) agents with reusable and editable guidance for solving complex tasks. Yet their effectiveness depends not only on skill quality, but also on whether the policy can translate the provided guidance into appropriate actions. However, methods specifically designed to improve this skill-utilization ability remain largely underexplored. In practice, skill-based agents are commonly trained with reinforcement learning objectives centered on task-level rewards, which offer limited supervision and struggle to capture subtle differences...

AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, industry standards and regulation can keep pace with increasingly powerful models.

a quiet day lets us find some connections among recent themes

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5 , where I had Claude Fable 5 build a full working game from a premise I generated with GPT-3 and DALL-E four years ago . I decided to pose the exact same prompt to Codex Desktop running GPT-5.6 Sol Ultra - the mode where Sol makes aggressive use of sub-agents - to see how it would do. It produced a much better game! Here's Moonlight & Mayhem - GitHub repository here , including the textures and prompts it generated using gpt-image-2 . Your browser d...

What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding) temperature, the subordinate neither copies its boss nor returns to how it behaves on its own; instead, it adopts an entirely different behavior. The bos...

LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the agent's context without weight updates. Recent methods refine skills through iterative task execution, failure diagnosis, and trajectory-guided text-space updates. However, existing frameworks lack explicit diagnosis--outcome feedback and treat deletion as a generic edit operation rather than a dedicated mechanism for consolidating accumulated knowledge. We introduce SkillProx, a proximal-gradient-inspired forward--b...

Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving topical fit while allowing emotionally important traces to enter the prompt. Across three controlled conflict scenarios, the full architecture retrieved mor...

Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can inspect datasets, generate code, and produce analyses end-to-end. However, we show that they frequently make subtle inferential errors that lead to incorrect conclusions despite correctly executed analyses. Existing benchmarks fail to capture this failure mode, as they rarely assess whether a reported p-value is statistically valid given the assumptions underlying the data. We address this gap by building P-Bench, a be...

Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represents observations as keyed precedents and revokes active precedents when fresh evidence contradicts ...

Cloudflare has introduced Kitesurf, a cloud-hosted browser designed for AI agents instead of people. The company says the browser uses less computing power than Chromium for common automation tasks, helping developers build browser-based AI agents more efficiently.

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce $A^2E$ (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. $A^2E$ leverages our newly proposed Agent Task Protocol (ATP) to enable ...

The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents execute more of the engineering process. Realizing that end-state requires more than better code generation: it requires assurance closure, meaning that the system can establish what must be true, determine and obtain appropriate evidence, judge the credibility of that evidence, preserve its validity through change, and use the resulting uncertainty to bound agent authority. Existing work already provides many of the necessary mechanisms across...

Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been conducted. In this work, we empirically compare programmatic tool calling (PTC) to native JSON tool calling across 14 language models on BFCL v4. In the programmatic tool calling paradigm, tools are ex...

Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time. Since the number of games needed is unknown, fixed-budget evaluations either keep paying after the result is settled or stop before the agents can be told apart, while naive optional stopping with an ordinary confidence interval invalidates the stated level. We make such an evaluation stop as soon as its evidence suffices, with the guarantee intact. The Action-Informed Value Assessment Tool (AIVAT) reduces variance in imperfect-information games...

We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our work as a compliance or commons overlay on a deployer. One governance period is an extensive form game in which verified human stakeholders arrive sequentially and contribute, on a provision or a reje...