The Archive

Cognition makes Devin, the first and arguably most successful AI coding agent. But famed coder Wu says it isn't designed to supplant human programmers.

Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles. The rise of LLM-based scientific agents creates an opportunity to automate this process. Such a system must support the full research lifecycle, maintain structured persistent memory across projects, and improve its own research procedures over time. However, existing systems either partially satisfy or fail to satisfy these requirements, leaving a gap for a unified automated scientific research system. As...

GPU kernels are the workhorse of modern deep learning, and optimizing them (via evolutionary search or coding agents) usually requires repeated measurement on target hardware. While these measurements provide the ground-truth signal necessary for kernel search, they are costly, because each evaluation of a kernel requires compilation and repeated execution on a GPU. As improvements in LLM inference reduce the cost of writing novel kernels and LLM-driven searches scale to large search budgets, on-device evaluation becomes a bottleneck. To address this, we study how LLMs can serve as selective ...

Mixture-of-Experts (MoE) has become the dominant architecture for frontier language models. To meet this demand, production frameworks have built optimized MoE training stacks over years of engineering effort. Yet evolving these stacks for new architectures and system optimizations remains expensive. With the rise of AI coding agents, they could automate parts of training-framework development and accelerate this evolution. But applying them to these existing frameworks carries hidden costs, invisible to today's throughput-only evaluations. We name this missing dimension agent-task efficiency...

In this work we study agents in simulated bargaining scenarios, where a buyer and a seller communicate through a text channel and attempt to negotiate mutually beneficial trades, under different information regimes (complete information, information asymmetry or mutual uncertainty). We evaluate their performance w.r.t. game-theoretical solutions and further investigate their honesty (their tendency to disclose or withhold information or to mislead and deceive) as well as their credulity (their tendency to trust or distrust information provided by the other agent). We study zero-shot LLM agent...

Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approximation are therefore essential. Relational Reinforcement Learning (RRL) offers a way to reason about objects and their relations, and the CARCASS framework by Martijn van Otterlo demonstrates how logical representations can model Markov Decision Processes (MDPs) in first-order domains. Originally implemented in Prolog, CARCASS leverages domain knowledge to create powerful abst...

The people deciding that AI can replace your job are also the ones least likely to understand what your job truly involves, according to Box founder Aaron Levie, who pointed to this as an example of “AI psychosis.” Indeed, ClickUp recently cut 22% of its workforce for AI agents, tech layoffs in 2026 are already nearly matching all of 2025, […]

Artificial Intelligence (AI) agents personalize their responses by tailoring explanations to users' backgrounds, interests, and prior interactions, referred to as contextualization. Personalization has been identified as a persuasive strategy in politics or in marketing. However, the persuasive effect of contextualization in everyday tasks, where users often lack prior knowledge, remains unclear. We conducted a $2\times2$ between-subjects experiment ($N = 380$) examining how contextualization, combined with conversational warmth, shapes reliance and persuasiveness of an AI assistant arguing a...

LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building such person-grounded agents remains difficult because actionable knowledge associated with a person or role is usually embedded in heterogeneous traces rather than written as clean instructions. Existing memory and persona systems capture fragments of this evidence, while skill frameworks provide portable packaging formats; however, there is no end-to-end workflow for distilling these traces into inspectable, correcta...

Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where agents may actively acquire observations through sequential changes in yaw, pitch, and zoom. The benchmark contains 2,207 globally distributed street-view panoramas and measures four complementary capab...

Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage approach consisting of a rule-based heuristic (about 6000 matches) followed by zero-shot classification (518 kept). The resulting categories include token efficiency (166), new natural languages (106), and oversight evasion (59). We conduct both quantitative and qualitative analyse...

As AI agents move from experiments to production, AWS, Cloudflare, and others are redesigning cloud infrastructure for a future dominated by machine-generated internet traffic instead of human users.

Undisclosed addition in jqwik instructed AI coding agents to delete app output.

80% Devin Commits, Spec-to-PR Workflows, Full VMs, Agent Memory, and PMs Shipping Code

Are AI agents tools, co-authors, or researchers? We present a quantified case study ($N=1$): a physicist supervising an AI coding agent (Claude Code, Sonnet and Opus models) over 12 work days and 57 sessions to build CLAX-PT, a differentiable one-loop perturbation theory module in JAX. We documented and classified 15 supervision events by intervention level. The agent resolved ten autonomously by iterating against oracle tests. Two more by the physicist's domain knowledge. The three it could not -- all evaded oracle detection -- share a common property: the agent treated symptom reduction as ...

Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic probability axioms even when every component is locally coherent. We formalise this locally coherent, globally incoherent failure via the compositional residual eps*, the L2 distance from the composed quote to the joint coherent polytope, computable at runtime from system output and the declared cross-component coupling constraints. A product-structure dichotomy characterises when local coherence suffices, and a Rayleigh-quotient prediction mat...

Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language Models can judge the methodological viability of a research idea before expending time and computational resources. We introduce SoundnessBench, a curated benchmark of 1,099 machine-learning research proposals reconstructed from ICLR submissions, labeled with reviewer soundness sub-scores, and audited against source papers. SoundnessBench should be interpret...

We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models across 17 simulated agentic deployment scenarios that incentivize sabotage. We find Gemini models misbehave in about 2-3% of our simulated trajectories. Many of these cases are explained by "overeagerness" in Gemini models resulting in both excessive role-playing and goal-seeking behavior. In contrast to other alignment auditing approaches, Gram is designed to specifically evaluate misalignment and intentional sabotage in agentic coding and resear...

Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonverbal cues, such as nods, smiles, and gestures. To support successful human-agent interaction, agents must model full-duplex audiovisual conversation; however, existing full-duplex benchmarks evaluate only speech. In this work, we present VideoFDB, the first benchmark to evaluate full-duplex audio-visual-to-audio-visual (AV2AV) conversational agents. VideoFDB contributes (i) 237 dyadic clips spanning 11 nonverbal conversational dynamics from real...

Today we're introducing dynamic workflows in Claude Code. Claude now writes its own orchestration scripts, fans work out across tens to hundreds of parallel subagents in a single session, and verifies its own results before anything reaches you. Work you'd normally plan in quarters can finish in days. Built for the tasks a single pass can't handle: codebase-wide bug hunts, security and optimization audits, large migrations and language ports, and high-stakes work where you want adversarial agents trying to break the answer before you see it. Progress is checkpointed, so long runs survive int...

The new Opus model comes with a tool called Dynamic Workflows, for coordinating swarms of subagents.

I was at 88% last night and woke up until 4pm to optimize my agents so I can work during the weekend. But after waking up, my usage is all 0 now, I checked in the app, on the web, all showing zero. Did AI God grant me a wish? Edit: wow Opus 4.8 is here, AI God really grant us all a wish

Sesame’s new iOS app brings its conversational AI agents to the public, offering more natural back-and-forth interactions designed to feel less like traditional chatbots and more like talking to a person.

Hi! Andi from Hugging Face here! My team has been working over the last few months on creating a super smooth local experience for conversations with Reachy Mini, see the video! We hope people can extend this into tons of different cool use-cases. We wrote a blog explaining how to set this up, and how to modify it for tons of different use cases. Even if you don't have a Reachy Mini, you can use this as a roadmap for amazing voice agents: [https://huggingface.co/blog/local-reachy-mini-conversation](https://huggingface.co/blog/local-reachy-mini-conversation) Hope you enjoy it!

Imagine a world run by AI agents. What does it look like? What are the values or societal priorities? Is it a safer or more dangerous world? Enterprise AI startup Emergence AI is trying to find out. The company just launched Emergence World, a research lab dedicated to stress-testing the long-term viability of continuously-running AI systems. The organization ran five 15-day simulations, each governed by a different AI: Claude, ChatGPT, Grok, Gemini, and a fifth simulation run by a mix of models to see what kind of world each one builds, and whether it holds. Each simulation netted wildly d...

sqlite AGENTS.md SQLite gained an AGENTS.md file five days ago - but it's not intended for their own development, it's presumably aimed at people who are pointing agents at the SQLite codebase. It includes: SQLite does not accept pull requests without prior agreement and/or accompanying legal paperwork that places the pull request in the public domain. However, the human SQLite developers will review a concise and well-written pull request as a proof-of-concept prior to reimplementing the changes themselves. SQLite does not accept agentic code. However the project will accept agentic bug repo...

Anthropic recently published an incredibly deep breakdown analyzing millions of real human-agent tool calls across their public API, and they shared a breakdown of where these agents are being deployed. They said “Software engineering makes up roughly 50% of all agentic activity on their platform”. Everything else: sales, marketing, finance, legal is sitting down in the single digits. A lot of the initial commentary around this has been along the lines of: *"Oh, look, AI agents only work for coding. They haven't cracked the rest of the enterprise yet."* But if you’ve tried to build and dep...

Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when images are included, the user-specific information needed for later questions is typically recoverable from text alone, and most memory systems reduce image turns to generic captions. Yet images often carry personal information that text rarely states -- both explicit evidence, such as recurring user-associated entities, and implicit evidence, such as latent user facts inferred from visual or multimodal cues. We introduce a benchmark for personal vi...

In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.org has anchored the FAIR principles (Findable, Accessible, Interoperable, and Reusable) for machine-actionable data and enabled discovery tools like Google Dataset Search. However, the rise of Large Language Models (LLMs) capable of navigating the unstructured web raises a fundamental question: Is semantic metadata still necessary for agentic data discovery, or can agents reliably retrieve actionable data directly from the web? We present a com...

Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents are more practical specialization targets, but they remain substantially weaker and exhibit uneven domain-specific failures. A straightforward remedy is to synthesize large-scale training data for the target domain, yet we find that this naive approach yields only marginal improvements. Building on this observation, we introduce LearnWeak, an annotation-free specialization framework for small computer-use agents th...