Knowledge catalogue
arXiv:2606.11070v1 Announce Type: cross Abstract: Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However,
arXiv:2606.10080v1 Announce Type: cross Abstract: Generative models have shown remarkable progress in a variety of domains such as protein design, but such power enables the opaque generation of hazar
arXiv:2606.10423v1 Announce Type: new Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference
arXiv:2606.07845v1 Announce Type: cross Abstract: We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a
arXiv:2606.09826v1 Announce Type: cross Abstract: Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a s
arXiv:2601.19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they coo
arXiv:2606.07555v1 Announce Type: cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways. When this works, the
arXiv:2606.07968v1 Announce Type: cross Abstract: Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's quest
arXiv:2606.07929v1 Announce Type: new Abstract: Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes. Here we p
arXiv:2606.06758v1 Announce Type: new Abstract: Final-answer accuracy, retrieval recall, and citation overlap do not by themselves identify whether a long-context or retrieval-augmented language model
arXiv:2606.06797v1 Announce Type: new Abstract: Cultural-aspect work on large language models is dominated by a negative target: which outputs to suppress. We argue that a constructive counterpart is
arXiv:2606.06696v1 Announce Type: cross Abstract: Vision and language models (VLMs) hold immense promise to transform biomedical imaging workflows, from detecting lesions in chest X-rays to profiling
arXiv:2606.06694v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly assuming an intermediary role in housing search through the integration of listing platforms within conversat
arXiv:2602.07025v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing t
This is exactly right. People are starting to look for cheaper model alternatives and realizing two things at once: open-source models are already very good, and the ability to train and serve them ef
arXiv:2512.03086v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource progra
arXiv:2606.05792v1 Announce Type: new Abstract: TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language stil
arXiv:2606.05606v1 Announce Type: cross Abstract: LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed ro
arXiv:2606.06322v1 Announce Type: new Abstract: GUI agents - vision-based models that control desktops, web browsers, and mobile devices through graphical user interfaces - promise to automate a wide
arXiv:2606.06468v1 Announce Type: new Abstract: We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is
arXiv:2606.05875v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing ret
arXiv:2606.05382v1 Announce Type: new Abstract: Multi-table question answering requires models to retrieve relevant evidence, link schemas, and perform compositional reasoning across relational tables
arXiv:2602.09574v2 Announce Type: replace Abstract: Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment often imposes a fixed per
arXiv:2606.05553v1 Announce Type: new Abstract: Role-playing language agents (RPLAs) should play characters whose values and behavior evolve as the story progresses, not maintain a fixed persona. Exis
arXiv:2603.26233v2 Announce Type: replace Abstract: As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspeci
arXiv:2606.05421v1 Announce Type: new Abstract: When a text is translated, does the translation retain the complexity of the original? We introduce ComplexityMT, a new challenge for assessing how text
arXiv:2606.06306v1 Announce Type: new Abstract: Factual sycophancy occurs when a language model abandons a correct, verifiable answer under social pressure. Because a flip occurs only when pressure to
arXiv:2606.06203v1 Announce Type: new Abstract: Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study le
Here’s this week’s shipping recap 👇 — Nano Banana 2 & Nano Banana Pro are now GA and available via the Gemini Enterprise Agent Platform, Gemini API, and in @GoogleAIStudio —Co-Scientist, our new multi
arXiv:2606.05570v1 Announce Type: new Abstract: Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often invol
Wow Ideogram-4.0 is immediately going into my @ComfyUI library of models. Ideogram even joins the top 10 all-around image leaderboard joining Microsoft, Google, Grok and OpenAI. In the Image Arena: op
arXiv:2606.04755v1 Announce Type: cross Abstract: We present Archi, an open-source, end-to-end framework for scientific collaborations that combines the systematic ingestion and organization of hetero
arXiv:2606.05085v1 Announce Type: cross Abstract: The title of a research paper conveys its primary idea and, occasionally, its conclusions in a clear and concise manner. Choosing an appropriate title
arXiv:2510.01529v3 Announce Type: replace Abstract: Ball et al. recently established that prompt filtering for AI alignment faces a fundamental barrier: under standard cryptographic assumptions, no fi
arXiv:2606.04141v1 Announce Type: cross Abstract: LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt inj
arXiv:2606.04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding ext
arXiv:2606.04433v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in
arXiv:2606.04592v1 Announce Type: cross Abstract: LLM-based digital twins promise to scale and accelerate market research, but most published twins are either coarse persona bots conditioned on a few
arXiv:2602.16149v2 Announce Type: replace Abstract: Instruction-guided image-to-image (I2I) editors are increasingly used in consumer and professional visual workflows, where trustworthiness depends n
arXiv:2606.04127v1 Announce Type: new Abstract: Medical question answering is a high-stakes setting where factual errors can have serious consequences. Retrieval-augmented generation (RAG) is widely v
arXiv:2606.03811v1 Announce Type: cross Abstract: A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited pr
arXiv:2606.02798v1 Announce Type: new Abstract: Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks
arXiv:2606.03829v1 Announce Type: new Abstract: Financial-research answers are decision-relevant only when another analyst can audit how they were produced: which source was chosen, which period and a
arXiv:2606.02741v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systemati
arXiv:2606.03437v1 Announce Type: new Abstract: Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, lit
arXiv:2606.03986v1 Announce Type: new Abstract: Previous work has evaluated physics reasoning in foundation models using synthetic or semi-synthetic scenes and visual question-answering tasks. However
arXiv:2606.03357v1 Announce Type: cross Abstract: When prompting SLMs for psychometric assessments, researchers assume the outputs reflect semantic reasoning. We evaluate this premise across 13 open-w
arXiv:2606.02211v1 Announce Type: cross Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduce
arXiv:2606.01637v1 Announce Type: cross Abstract: Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a m
arXiv:2606.01679v1 Announce Type: new Abstract: Multimodal LLMs are increasingly used to assist scientific peer review, where a core requirement is verifying whether claims in a paper are supported by
arXiv:2606.01528v1 Announce Type: new Abstract: In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this. Effective exploratio
arXiv:2606.01914v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly atten
arXiv:2606.02430v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through di
arXiv:2606.02493v1 Announce Type: new Abstract: Large language models (LLMs) are being increasingly used to answer subjective, information-seeking questions, where users are sensitive to how responses
arXiv:2606.01476v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitig
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode colla
arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both f
arXiv:2606.00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with
arXiv:2605.30538v1 Announce Type: new Abstract: Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records
arXiv:2605.30738v1 Announce Type: new Abstract: Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language mode