Knowledge catalogue
arXiv:2609.38891v1 Announce Type: new Abstract: Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach d
arXiv:2609.39154v1 Announce Type: cross Abstract: Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emer
arXiv:2609.39340v1 Announce Type: new Abstract: Electrolyte formulation design requires balancing multiple physicochemical properties, yet existing models often focus on a limited subset. Learning eac
arXiv:2609.39566v1 Announce Type: new Abstract: Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected ev
arXiv:2609.39600v1 Announce Type: cross Abstract: Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We vi
arXiv:2609.39601v1 Announce Type: cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fa
arXiv:2609.38480v1 Announce Type: cross Abstract: Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present
arXiv:2609.38181v1 Announce Type: new Abstract: Survival analysis estimates time-to-event outcomes from patient covariates and is widely used for medical risk assessment. Patients seeking prognostic i
arXiv:2609.40169v1 Announce Type: new Abstract: Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve
arXiv:2609.39507v1 Announce Type: new Abstract: General-purpose agents can plan, use tools, and revise their behavior from feedback, but it remains unclear whether these capabilities transfer from dig
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-t
arXiv:2609.38392v1 Announce Type: new Abstract: Personas used to seed LLM social simulations face a cold-start problem: existing methods lack a principled basis for deciding which attributes to includ
arXiv:2609.39982v1 Announce Type: cross Abstract: Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor c
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long
At OpenAI's annual DevDay conference, the company pulled out all the stops to compete with its rivals - primarily Meta, whose Muse AI agent platform has seen early runaway success. CEO Sam Altman walk
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac
arXiv:2609.39229v1 Announce Type: cross Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary fro
Records that span multiple pages: 85.5% → 96.5%. That's where we most often see customers get stuck with existing tools. With citations on every value, the output is easy to trust. Great work from the
arXiv:2609.39045v1 Announce Type: new Abstract: Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a play
arXiv:2609.40198v1 Announce Type: cross Abstract: Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused
arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit polic
arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorith
arXiv:2609.38612v1 Announce Type: new Abstract: As natural language drives more applications, language models increasingly run inside programs as decision components: the program sends them the curren
arXiv:2609.38325v1 Announce Type: new Abstract: We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build mo
Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentic plus) are tuned for value accuracy and grounding. Our ext
Turns out sometimes, you can just rebuild things. Congrats to the team on the launch! 🦙 🚀 Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (
arXiv:2609.39195v1 Announce Type: new Abstract: Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own mot
arXiv:2609.38512v1 Announce Type: new Abstract: Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that
arXiv:2603.14733v2 Announce Type: replace Abstract: Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos
arXiv:2609.32754v2 Announce Type: replace Abstract: Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequ
arXiv:2607.11849v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on high-school and competition-level mathematics, yet their capabilities on advanc
arXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cover
arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet
arXiv:2609.37713v1 Announce Type: new Abstract: Existing product matching benchmarks primarily contain English-language product data and are often dominated by a single product category, such as elect
arXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont
arXiv:2609.36746v1 Announce Type: new Abstract: Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. How
Follow-up to my post from about two weeks ago. A lot has changed since then, so I wanted to post an update on where the backend is now. Where the green architectures stand When I posted last time, 7 a
Grok 4.7 rank 1 on AA cyber index Grok 4.7 xHigh ranks #1 in Artificial Analysis Cyber Index It's a powerful frontier model performing at the highest level in enterprise cyber defense Outperforming Fa
arXiv:2609.36641v1 Announce Type: cross Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. H
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.36139v1 Announce Type: cross Abstract: As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outpu
arXiv:2609.35779v1 Announce Type: cross Abstract: Given recent achievements of large language models (LLMs), frontier models are expected to perform well on Bayesian reasoning tasks, at least as well
arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. H
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guid
arXiv:2609.36246v1 Announce Type: new Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressively
arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scatte
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that age
arXiv:2609.36059v1 Announce Type: cross Abstract: Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts,
arXiv:2609.36692v1 Announce Type: cross Abstract: Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram represent
Maggie Eastland / Bloomberg: OpenAI says individuals associated with Moonshot AI played a significant role in a coordinated model-distillation campaign that began in early July — OpenAI accused its Ch
arXiv:2609.35549v2 Announce Type: replace Abstract: Rare-disease diagnosis is a long-tail reasoning problem: phenotypes are incomplete, individual disorders are sparsely documented, and relevant evide
arXiv:2609.37089v1 Announce Type: new Abstract: Real-world videos provide rich demonstrations of manipulation, but turning them into reusable robot skills requires visually aligned environments, execu
arXiv:2609.35890v1 Announce Type: new Abstract: Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to rev
arXiv:2609.36605v1 Announce Type: new Abstract: Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We intro
arXiv:2609.37842v1 Announce Type: cross Abstract: Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influen
New York Post: Sources: the US FTC is expanding a sweeping probe of Anthropic, OpenAI, and other frontier AI labs, and plans to issue formal demands to turn over information — WASHINGTON — The Federal
arXiv:2512.03284v2 Announce Type: replace Abstract: Spatial reasoning in large-scale 3D environments remains challenging for current vision--language models, which are typically constrained to room-sc
arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control c
arXiv:2609.38043v1 Announce Type: new Abstract: Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated us
arXiv:2609.37519v1 Announce Type: cross Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched d