Knowledge catalogue
arXiv:2608.14277v1 Announce Type: cross Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context r
arXiv:2608.13221v1 Announce Type: new Abstract: The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models
A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. The post
arXiv:2608.11047v1 Announce Type: new Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains compar
arXiv:2608.05242v1 Announce Type: cross Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly a
arXiv:2608.04434v1 Announce Type: new Abstract: Recent large language models (LLMs) have demonstrated remarkable progress in constraint-aware navigation, maze reasoning, and graph reasoning. However,
arXiv:2608.02831v1 Announce Type: cross Abstract: Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning
arXiv:2608.01534v1 Announce Type: new Abstract: Hard symbolic-reasoning tasks such as Sudoku, maze pathfinding, and ARC remain challenging for LLMs due to their fixed-depth autoregressive reasoning, w
arXiv:2608.02442v1 Announce Type: cross Abstract: Scientific reasoning benchmarks typically evaluate large language models (LLMs) using final-answer accuracy. However, a correct answer does not necess
arXiv:2607.27631v1 Announce Type: cross Abstract: Reinforcement learning has emerged as an effective paradigm for enhancing the mathematical reasoning capabilities of large language models. Among exis
arXiv:2607.26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation mod
arXiv:2607.20638v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in code generation and reasoning, yet their ability to perform temporal reasoning ove
arXiv:2607.20197v1 Announce Type: new Abstract: Remote sensing image editing aims to modify remote sensing images according to natural language instructions while preserving geographic rules and senso
arXiv:2607.12497v1 Announce Type: new Abstract: Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large langua
arXiv:2607.12267v1 Announce Type: cross Abstract: Language agents that interleave reasoning and tool use degrade sharply as reasoning chains lengthen, even when each individual step is easy. We trace
arXiv:2508.10956v3 Announce Type: replace-cross Abstract: Inspired by human categorization, visual reasoning about object properties, such as physical attributes and functions, involves identifying an
arXiv:2502.15631v2 Announce Type: replace-cross Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and reinforcement learning.
arXiv:2606.18089v2 Announce Type: replace Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming l
arXiv:2607.00115v1 Announce Type: new Abstract: This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories.
arXiv:2606.26476v1 Announce Type: cross Abstract: Warm-started diffusion samplers accelerate iterative inference, but it is rarely clear which part of the pipeline carries the gain. We study extbf{ret
arXiv:2606.27103v1 Announce Type: new Abstract: Humans flexibly adapt their reasoning strategies to the requirements of a given problem. Large language models (LLMs) have performed well on many cognit
arXiv:2606.11211v1 Announce Type: cross Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is wi
arXiv:2509.23248v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and a
arXiv:2603.23183v2 Announce Type: replace-cross Abstract: Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generat
arXiv:2606.08974v1 Announce Type: new Abstract: Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reason
arXiv:2601.09402v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge into the generation process. Benefiti
arXiv:2606.03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little
arXiv:2602.18645v2 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full
arXiv:2606.00229v1 Announce Type: cross Abstract: Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control
arXiv:2603.03031v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning
arXiv:2602.09276v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning and its variants have substantially improved the performance of language models on complex reasoning tasks, y
arXiv:2605.30587v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has significantly improved the reasoning ability of large vision-language models (LVLMs) by verbalizing intermediate re
arXiv:2605.28919v1 Announce Type: cross Abstract: Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In th
arXiv:2508.19202v3 Announce Type: replace Abstract: Scientific problem solving poses unique challenges for LLMs, requiring both deep domain knowledge and the ability to apply such knowledge through co
arXiv:2510.22437v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reas
arXiv:2605.30343v1 Announce Type: cross Abstract: To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the fin
arXiv:2603.16673v4 Announce Type: replace-cross Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-
arXiv:2605.28006v1 Announce Type: cross Abstract: Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs are observable, the underlying reasoning patterns re
arXiv:2605.28160v1 Announce Type: new Abstract: Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to
arXiv:2605.27824v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representation
arXiv:2510.08525v3 Announce Type: replace Abstract: Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information
arXiv:2605.27014v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Re
arXiv:2605.26735v1 Announce Type: new Abstract: Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior wor
arXiv:2605.24998v1 Announce Type: new Abstract: Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data wit
arXiv:2603.05143v3 Announce Type: replace Abstract: Understanding reasoning in large language models is complicated by evaluations that conflate multiple reasoning types. We isolate analogical reasoni
arXiv:2605.23997v1 Announce Type: cross Abstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they
arXiv:2605.20177v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is prima
arXiv:2605.16416v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong performance on general multimodal reasoning, yet remain challenged in integrating nonlocal visual i
arXiv:2601.06943v2 Announce Type: replace-cross Abstract: In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed ac
arXiv:2605.14457v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its b
arXiv:2603.12529v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables th
arXiv:2605.11856v1 Announce Type: cross Abstract: Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on
arXiv:2605.08965v1 Announce Type: new Abstract: Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains ch
arXiv:2605.08802v1 Announce Type: new Abstract: Due to the potential for exploratory reasoning of Latent Visual Reasoning, recent works tend to enable MLLMs (Multimodal Large Language Models) to perfo
arXiv:2605.07357v1 Announce Type: new Abstract: Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, ex
arXiv:2605.04313v1 Announce Type: new Abstract: Causal reasoning in natural language requires identifying relevant variables, understanding their interactions, and reasoning about effects and interven
arXiv:2605.04078v1 Announce Type: new Abstract: Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent metho
arXiv:2501.19201v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Mod
arXiv:2509.23330v3 Announce Type: replace Abstract: Large language models (LLMs) have achieved significant advancements in reasoning capabilities through reinforcement learning (RL) via environmental
// When to Retrieve During Reasoning // Pay attention to this one, AI devs. (bookmark it) Most RAG systems retrieve once, before the model starts reasoning. Large reasoning models like o1 and R1 don't