Knowledge catalogue
arXiv:2605.07339v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a s
arXiv:2605.08070v1 Announce Type: new Abstract: A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most c
Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and s
arXiv:2605.03361v2 Announce Type: new Abstract: As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organizati
arXiv:2603.10384v2 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework th
arXiv:2605.02910v1 Announce Type: cross Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative
arXiv:2605.03050v1 Announce Type: new Abstract: Millions of users turn to AI models for their information needs. It is conceivable that a large number of user queries contain assumptions that may be f
arXiv:2601.04809v5 Announce Type: replace Abstract: Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on
Today we're releasing ZAYA1-8B, a reasoning MoE trained on @AMD and optimized for intelligence density. With <1B active params, it outperforms open-weight models many times its size on math and reason
arXiv:2605.01657v1 Announce Type: new Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic in
arXiv:2605.01324v1 Announce Type: new Abstract: Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains
arXiv:2510.09883v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but th
arXiv:2601.17467v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination det
arXiv:2605.01489v1 Announce Type: cross Abstract: Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents
arXiv:2605.01939v1 Announce Type: new Abstract: Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent
arXiv:2605.01111v1 Announce Type: cross Abstract: In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightwe
arXiv:2504.10368v4 Announce Type: replace Abstract: This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal tok
arXiv:2508.07630v2 Announce Type: replace Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task
arXiv:2510.26020v2 Announce Type: replace Abstract: Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls t
arXiv:2605.00380v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diver
arXiv:2510.00072v2 Announce Type: replace Abstract: Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. W
arXiv:2604.27960v1 Announce Type: new Abstract: Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical incons
arXiv:2604.27375v1 Announce Type: new Abstract: Reasoning photo retouching has gained significant traction, requiring models to analyze image defects, give reasoning processes, and execute precise ret
arXiv:2604.26288v1 Announce Type: cross Abstract: Chest X-ray interpretation is one of the most frequently performed diagnostic tasks in medicine and a primary target for AI development, yet current v
arXiv:2603.12249v2 Announce Type: replace-cross Abstract: Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faith
arXiv:2604.25800v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing comple
arXiv:2604.25907v1 Announce Type: new Abstract: Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewar
arXiv:2603.08592v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space r
arXiv:2601.14952v2 Announce Type: replace-cross Abstract: While large language models now handle million-token contexts, their capacity for reasoning across entire document repositories remains largel
arXiv:2604.23348v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in
arXiv:2512.23213v3 Announce Type: replace-cross Abstract: We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for
arXiv:2604.23198v1 Announce Type: new Abstract: Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see extit{what is happening} but fail to
arXiv:2411.08027v3 Announce Type: replace-cross Abstract: Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) t
arXiv:2604.21495v1 Announce Type: cross Abstract: Numerical reasoning over expert-domain tables often exhibits high in-domain accuracy but limited robustness to domain shift. Models trained with super
arXiv:2604.21253v1 Announce Type: cross Abstract: While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logica
arXiv:2604.21346v1 Announce Type: new Abstract: Vision--language models (VLMs) often fail on abstract visual reasoning benchmarks such as Bongard problems, raising the question of whether the main bot
arXiv:2604.19766v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex
arXiv:2604.20749v1 Announce Type: new Abstract: Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver co
arXiv:2604.18988v1 Announce Type: new Abstract: Multimodal empathetic response generation (MERG) aims to generate emotionally engaging and empathetic responses based on users' multimodal contexts. Exi
arXiv:2604.19105v1 Announce Type: new Abstract: Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has
arXiv:2604.19193v1 Announce Type: new Abstract: Despite remarkable progress toward general-purpose video models, a critical question remains unanswered: how far are these models from achieving true mu
arXiv:2604.19172v1 Announce Type: new Abstract: The rapid advancement and widespread adoption of Large Language Models (LLMs) have elevated the need for reliable AI-generated content (AIGC) detection,
arXiv:2604.19060v1 Announce Type: new Abstract: Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improv
arXiv:2604.17188v1 Announce Type: new Abstract: Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual
arXiv:2601.21278v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) are good at recognizing the global location of a photograph -- their geolocation prediction accuracy rivals the
arXiv:2601.21244v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under lim
arXiv:2506.00772v2 Announce Type: replace-cross Abstract: Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabiliti
arXiv:2604.16929v1 Announce Type: new Abstract: The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and i
arXiv:2603.27437v2 Announce Type: replace Abstract: Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This
arXiv:2601.15724v2 Announce Type: replace Abstract: Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning
arXiv:2604.15851v1 Announce Type: cross Abstract: Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-leve
arXiv:2509.25300v4 Announce Type: replace-cross Abstract: While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement lear
arXiv:2604.16263v1 Announce Type: new Abstract: Coordinating multi-robot systems (MRS) to search in unknown environments is particularly challenging for tasks that require semantic reasoning beyond ge
arXiv:2604.16022v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from text processors to autonomous agents, evaluating their social reasoning in embodied multi-agent settings
arXiv:2509.05367v4 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classificati
arXiv:2604.15148v1 Announce Type: cross Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to perform search-augmented reasoning. However, existin
arXiv:2512.15925v2 Announce Type: replace Abstract: Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences about narrative intent or judgments about characte
arXiv:2604.13706v1 Announce Type: new Abstract: Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning
arXiv:2604.13062v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated strong capabilities in code generation and text synthesis, yet their potential for sym
arXiv:2604.14041v1 Announce Type: new Abstract: Daily scenarios are characterized by visual richness, requiring Multimodal Large Language Models (MLLMs) to filter noise and identify decisive visual cl