CEO-Bench: Can Agents Play the Long Game?
arXiv:2606.18543v2 Announce Type: replace Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real
Knowledge catalogue
arXiv:2606.18543v2 Announce Type: replace Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real
arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet
arXiv:2502.16022v3 Announce Type: replace Abstract: OpenNotes gives patients access to their EHR notes, but dense medical jargon limits comprehension. We evaluate closed-source and open-source LLMs fo
arXiv:2607.20251v1 Announce Type: new Abstract: Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics.
Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behavior is often harder than writing the edit. Harness Handbook
arXiv:2510.05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a singl
LlamaParse can't solve a conjecture, but it can parse this as a PDF 🫡 Dinitz-Garg-Goemans conjecture is false. This graph theory problem was open for ~30 years. The graph below has fractional flow cos
OpenAI’s official incident page: eval agents exploited a zero-day to reach the internet and compromise Hugging Face during testing.
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlappe
arXiv:2607.19653v1 Announce Type: cross Abstract: Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature im
arXiv:2607.20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed trainin
arXiv:2607.19992v1 Announce Type: cross Abstract: tiny_schiller closes the small-language-model prototyping, fine-tuning, education, and research gap for German literary text, providing a single-file,
arXiv:2607.19794v1 Announce Type: new Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners p
arXiv:2607.19967v1 Announce Type: cross Abstract: Shippers are beginning to delegate carrier selection to large language model (LLM) agents. We ask what such delegation does to a freight matching mark
“If AI models were actually that good you could just tell them to solve open problems, make no mistakes and they would” … Oh Dinitz-Garg-Goemans conjecture is false. This graph theory problem was open
New for enterprises: OpenAI Presence helps companies deploy trusted voice and chat agents across customer and internal workflows. AI agents can answer questions, use company systems, take approved act
We benchmarked Gemini 3.6 Flash and Gemini 3.5 Flash Lite on document understanding. We compared against their prior versions - Gemini 3.5 Flash and Gemini 3.1 Flash Lite. 1️⃣ Gemini 3.6 Flash has rou
Incredibly proud of the Sakana AI team. We have developed an orchestration model right here out of Japan that achieves state-of-the-art performance on real-world cybersecurity benchmarks! 🎌 Introducin
OpenAI Group PBC today disclosed that two of its artificial intelligence models broke out of a controlled testing environment and hacked open-source AI platform Hugging Face Inc. to cheat on an intern
TL;DR: I’m reproducing the trait-persistence result from arXiv:2606.24014 on one RTX 3090. Before I can test persistence I need to install a trait via RL — and my GRPO run moves the trait only +2.4 po
Huge launch from @tryramp. Different steps in an agent workflow can use different models. This can help reduce costs significantly without sacrificing performance. Model routing will become a core par
arXiv:2607.13125v1 Announce Type: cross Abstract: We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turb
arXiv:2607.13386v1 Announce Type: new Abstract: Building foundation models for medical imaging requires pooling data across institutions, yet privacy regulations prohibit centralized aggregation. Exis
arXiv:2607.13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We intr
arXiv:2601.20379v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test
arXiv:2607.13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the fin
arXiv:2607.13044v1 Announce Type: cross Abstract: The European Patent Office (EPO) reported record filings in 2025, and the 2026 EPO Guidelines hold applicants strictly responsible for LLM-assisted co
arXiv:2607.12645v1 Announce Type: new Abstract: Generative modeling of longitudinal Electronic Health Records is increasingly important for privacy-preserving research, yet standard autoregressive mod
arXiv:2607.12195v1 Announce Type: cross Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three
Efficiency defined as score over active parameters. Removed all the models that were not on the pareto frontier. Yes I'm aware that artificialanalysis.ai aggregate benchmark isn't perfect, but I have
arXiv:2607.12056v1 Announce Type: new Abstract: Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and
arXiv:2607.13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task act
arXiv:2607.12884v1 Announce Type: new Abstract: Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication r
arXiv:2607.12260v1 Announce Type: new Abstract: Early screening of chronic kidney disease (CKD) is essential for preventing irreversible progression; however, many machine learning (ML)-based screenin
arXiv:2607.12625v1 Announce Type: new Abstract: OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a we
arXiv:2607.12696v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depe
arXiv:2607.11944v1 Announce Type: new Abstract: How do different components of iterative prompt optimization interact, and what happens when they are combined? We investigate this through MAGE (Memory
arXiv:2607.12605v1 Announce Type: cross Abstract: Large language models (LLMs) have improved automated program repair (APR), but two limitations remain. First, raw execution traces are often too large
arXiv:2607.11948v1 Announce Type: new Abstract: Regulated financial institutions operating under data-residency rules need tenant-owned language models that can run inside the institution's perimeter.
arXiv:2607.12385v1 Announce Type: new Abstract: A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activitie
arXiv:2607.12216v1 Announce Type: cross Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instr
arXiv:2607.12227v1 Announce Type: new Abstract: We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness co
arXiv:2607.11920v1 Announce Type: cross Abstract: Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck. We treat subjective expected ut
arXiv:2506.12339v2 Announce Type: replace-cross Abstract: We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language
arXiv:2607.11890v1 Announce Type: cross Abstract: Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale. Building on previous work that employed traditiona
someone just told me about this take* on CUA this is one of those gell mann moments for me lol. i've been watching computer use since World of Bits (Shi, fan, karpathy, hernandez & liang 2017). we wer
arXiv:2607.12042v1 Announce Type: new Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing m
arXiv:2607.12208v1 Announce Type: cross Abstract: We show that the Benjamini--Hochberg procedure can fail to control the false discovery rate (FDR) at its nominal level for correlated two-sided Gaussi
The Blender MCP is now part of the Hermes Agent MCP Catalog! Easily activate and install the Blender MCP by running `hermes mcp install blender` and ask your agent to start using blender. Hermes will
arXiv:2607.13003v1 Announce Type: cross Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user w
hello! Hello. We have reached 8M active users across Codex and ChatGPT Work. We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing every
Computer use in Codex got very good on PC. Asking it to do something on your computer and having the cursor move under the control of a ghost is one of the things that makes you viscerally realize how
Another big reason to use combination of frontier models. Chain-of-thought monitoring is treated as a reliable safety layer for agents. This DeepMind-affiliated study shows the layer can be argued out
playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha
arXiv:2510.22052v2 Announce Type: replace Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictat
arXiv:2607.08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components,
arXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m
arXiv:2607.08700v1 Announce Type: new Abstract: Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Befo
arXiv:2607.08404v1 Announce Type: cross Abstract: Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properti
arXiv:2607.08403v1 Announce Type: new Abstract: The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic pat