Knowledge catalogue
arXiv:2606.03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The har
arXiv:2606.03458v1 Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon dec
arXiv:2603.20508v2 Announce Type: replace-cross Abstract: Reasoning language models (RLMs) and the intermediate chains of thought they emit play an increasingly central role in multi-agent setups such
arXiv:2606.03092v1 Announce Type: new Abstract: Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by st
arXiv:2606.03629v1 Announce Type: new Abstract: Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently,
Engadget: A live blog of Microsoft Build 2026, where the company is set to unveil a Copilot “super app”, a new reasoning model, and Windows improvements for developers — We're expecting the presentati
arXiv:2606.00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning. In AXIOM, the language model function
arXiv:2606.02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approac
arXiv:2509.06948v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the
arXiv:2510.24081v2 Announce Type: replace Abstract: To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and
arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accu
arXiv:2509.06093v4 Announce Type: replace-cross Abstract: Materials synthesis procedures are predominantly documented as narrative text in papers, protocols, and laboratory records, placing them beyon
arXiv:2606.01336v1 Announce Type: new Abstract: As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a
Jay Peters / The Verge: Microsoft debuts MAI-Thinking-1, its first advanced reasoning AI model, trained “from the ground up on clean data, without distillation from third-party models” — MAI-Thinking-
Microsoft MAI models. Coming soon to Fireworks. Intelligence you control. End-to-end lineage you can prove. Fine-tune MAI reasoning models for your enterprise tasks. Your data. Your custom models. You
arXiv:2606.00832v1 Announce Type: new Abstract: Recent advances in agentic AI have enabled agents to complete complex tasks through tool use, reasoning, and multi-step planning. Yet existing benchmark
arXiv:2606.01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small mo
arXiv:2606.02010v1 Announce Type: cross Abstract: PlanarBench tests whether LLMs can draw planar graphs as ASCII art given only an edge list -- a spatial reasoning task that resists memorization becau
arXiv:2606.01145v1 Announce Type: new Abstract: While Reasoning Language Models (RLMs) are rapidly emerging as powerful tools for scientific research, their impact is primarily concentrated in 'hard s
arXiv:2606.00628v1 Announce Type: new Abstract: Self-distillation improves learning efficiency by rewriting reference answers as training data that better matches the model's own distribution. However
arXiv:2606.00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high perfo
arXiv:2605.31251v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to th
arXiv:2605.30747v1 Announce Type: new Abstract: Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. Ho
arXiv:2605.31096v1 Announce Type: new Abstract: While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language model
arXiv:2605.30942v1 Announce Type: new Abstract: Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representa
NVIDIA Cosmos 3 is an open-source omni-model designed for physical AI reasoning and action tasks, representing an advancement in multimodal AI systems. The model integrates multiple modalities to enab
arXiv:2605.29643v1 Announce Type: new Abstract: Cross-Video Reasoning (CVR) has emerged as a critical frontier in multimodal intelligence, requiring models to retrieve, align, and aggregate evidence d
arXiv:2605.29339v1 Announce Type: new Abstract: With the rapid advancement of multimodal large language models (MLLMs), models have demonstrated increasingly powerful multimodal capabilities. However,
arXiv:2605.29262v1 Announce Type: new Abstract: The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimiz
arXiv:2605.30295v1 Announce Type: cross Abstract: Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in realistic, electronic health record-congruent
arXiv:2605.29687v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-define
arXiv:2605.29123v1 Announce Type: new Abstract: Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard
arXiv:2603.23971v2 Announce Type: replace-cross Abstract: Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices
arXiv:2601.18116v2 Announce Type: replace Abstract: We argue that multi-document reasoning is constrained not only by how much text a model can read, but also by how limited query-time evidence budget
arXiv:2605.28301v1 Announce Type: new Abstract: Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics
arXiv:2605.27866v1 Announce Type: new Abstract: Evaluating AI tutor responses requires more than factual correctness: tutors must identify mistakes, locate errors, provide guidance, and offer actionab
arXiv:2601.03048v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) excel in semantic recognition but exhibit systematic failures in spatial reasoning tasks such as mental rotation. W
arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, P(y=1 mid o_{1
arXiv:2605.27636v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate excellent capabilities and performance for general reasoning tasks within the general public domain, t
arXiv:2605.27293v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing alg
arXiv:2505.18603v2 Announce Type: replace Abstract: Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly inform
arXiv:2605.26680v1 Announce Type: cross Abstract: Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing mo
arXiv:2511.06625v5 Announce Type: replace-cross Abstract: Low-dose chest computed tomography (LDCT) captures pulmonary and cardiac structures in a single scan, enabling joint assessment of lung and ca
arXiv:2508.18444v2 Announce Type: replace-cross Abstract: With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with huma
arXiv:2605.26239v1 Announce Type: new Abstract: In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmen
arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI
arXiv:2605.26362v1 Announce Type: cross Abstract: In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized
arXiv:2509.24050v4 Announce Type: replace Abstract: Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while re
arXiv:2605.25354v1 Announce Type: new Abstract: While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamical
arXiv:2605.25511v1 Announce Type: new Abstract: Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning ca
arXiv:2506.11027v3 Announce Type: replace-cross Abstract: Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming la
arXiv:2602.18527v2 Announce Type: replace-cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. T
arXiv:2602.10538v3 Announce Type: replace-cross Abstract: Agentic theorem provers combine a reasoning model, retrieval, search, and a proof assistant verifier, yet it remains unclear which components
arXiv:2605.23200v1 Announce Type: cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by ev
arXiv:2602.13985v2 Announce Type: replace Abstract: Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of
arXiv:2605.23315v1 Announce Type: cross Abstract: Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an
arXiv:2601.14652v5 Announce Type: replace Abstract: While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliv
arXiv:2605.22263v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged inf
arXiv:2605.22816v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of
Cursor Composer 2.5's is 3–18x cheaper than Opus 4.7 in Claude Code (medium reasoning), and 5–32x cheaper than GPT-5.5 in Codex (medium) based on API pricing This low Cost per Task isn't just driven b