SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2610.24090v1 Announce Type: new Abstract: Does persistent memory accumulated from previous attempts help an LLM agent solve new problems, and does memory design affect that benefit? We study programmatic Chinese-character drawing across five agent…
arXiv:2606.01810v5 Announce Type: replace Abstract: Current benchmarks for embodied vision-language planning inadvertently favor linguistic next-token prediction over physically grounded next-state reasoning. This rewards models that mimic statistical language priors rather than track true causal…
arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP)…
arXiv:2610.24006v1 Announce Type: new Abstract: Prominent AI safety discussions emphasize existential threats and catastrophic events, such as AI-enabled nuclear conflict or engineered biological outbreaks. This position paper argues that there is another type of…
arXiv:2610.24010v1 Announce Type: new Abstract: Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communicate them through text prompts.…
arXiv:2610.24051v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have made significant progress in producing high-fidelity images from natural-language prompts. Alongside this progress, numerous benchmarks have been developed to evaluate capabilities such as attribute…
arXiv:2610.24024v1 Announce Type: new Abstract: Rare diseases (RDs) affect an estimated 300 million people globally, leaving patients to navigate a protracted diagnostic odyssey constrained by clinical scarcity and fragmented medical knowledge. Artificial intelligence (AI)…
arXiv:2610.09624v2 Announce Type: replace Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds directly remains poorly understood.…
arXiv:2610.24061v1 Announce Type: new Abstract: As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To understand what makes such collaboration effective…
arXiv:2606.09659v2 Announce Type: replace-cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model…
arXiv:2602.03802v2 Announce Type: replace-cross Abstract: Modern distributed optimization methods mostly rely on traditional synchronous approaches, despite substantial recent progress in asynchronous optimization. We revisit Synchronous SGD and its robust variant, called $m$-Synchronous SGD, which…
arXiv:2610.25758v1 Announce Type: cross Abstract: In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience. For agents operating continually, existing…