SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2512.01775v2 Announce Type: replace Abstract: While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skills from known components) is often conflated…
arXiv:2607.03358v2 Announce Type: replace-cross Abstract: We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and natural datasets, we find that models rely on two distinct pathways…
arXiv:2610.30412v1 Announce Type: new Abstract: LLM-based chat agents are increasingly used for complex, multi-turn, multilingual medical triage in low- and middle-income countries (LMICs), yet evaluation methods focus on single-turn, English-only benchmarks that primarily test…
arXiv:2610.25123v2 Announce Type: replace Abstract: Agents now act on the Web, publishing packages, models and datasets through registry APIs, and remembering past verifications spares them the work. But a verdict rests on premises. When…
arXiv:2610.30379v1 Announce Type: new Abstract: LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role for…
arXiv:2605.22880v2 Announce Type: replace Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal,…
arXiv:2610.30374v1 Announce Type: new Abstract: The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine translation (NMT)…
arXiv:2602.16429v3 Announce Type: replace Abstract: Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as…
arXiv:2610.30161v1 Announce Type: new Abstract: Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but…
arXiv:2610.30162v1 Announce Type: new Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool use,…
arXiv:2610.30296v1 Announce Type: new Abstract: Large Language Models (LLMs) have accelerated research on low-resource and multilingual NLP, but their effectiveness in creating an equitable landscape remains unmapped. We analyze 1,158 peer-reviewed open-access papers published…
arXiv:2610.30349v1 Announce Type: new Abstract: LLMs are increasingly consulted for moral judgment. We aim to improve performance on such tasks by rewarding good arguments, on the premise that arguing well increases the likelihood of…