Knowledge catalogue
arXiv:2604.11556v1 Announce Type: cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to st
arXiv:2604.10517v1 Announce Type: new Abstract: Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for e
arXiv:2604.11502v1 Announce Type: cross Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate th
arXiv:2412.04272v5 Announce Type: replace-cross Abstract: In recent years, table reasoning has garnered substantial research interest, particularly regarding its integration with Large Language Models
arXiv:2604.11435v1 Announce Type: cross Abstract: Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-dr
arXiv:2604.09511v1 Announce Type: new Abstract: Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primari
arXiv:2604.06268v1 Announce Type: new Abstract: RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track
arXiv:2604.06995v1 Announce Type: new Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct s
arXiv:2604.08281v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of
arXiv:2610.18878v1 Announce Type: new Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requi
arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, com
arXiv:2610.15259v1 Announce Type: new Abstract: Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought. Each step reads cached keys and
arXiv:2610.19644v1 Announce Type: new Abstract: Typed decision models need an interface that can use additional reasoning while retaining candidate outputs. We train a shared candidate-answer reader o
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at
Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search, run code, or take acti
arXiv:2610.18694v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models rec
arXiv:2610.16357v1 Announce Type: new Abstract: Agentic video reasoning systems gather and assess video evidence across stages, selecting relevant spans as visual evidence for answering questions. New
arXiv:2610.16811v1 Announce Type: new Abstract: Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition
arXiv:2610.13672v1 Announce Type: cross Abstract: Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune a
arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world model
arXiv:2610.13832v1 Announce Type: cross Abstract: When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the
Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format rewards, and other GRPO tips & tricks. 00:00 Introduction an
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical
arXiv:2510.04532v2 Announce Type: replace Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting
arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supp
arXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir
arXiv:2610.09780v1 Announce Type: new Abstract: Diffusion models excel at image synthesis, but they remain limited in their ability to reliably satisfy structured spatial reasoning constraints. In con
arXiv:2610.09360v1 Announce Type: cross Abstract: Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such
arXiv:2610.08561v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedb
arXiv:2610.08659v1 Announce Type: cross Abstract: Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-base
arXiv:2610.05630v1 Announce Type: cross Abstract: Visual entailment (VE) asks whether an image supports, contradicts, or leaves undecided a textual hypothesis. Strong results come from fine-tuning lar
arXiv:2610.06439v1 Announce Type: new Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisa
arXiv:2507.07297v2 Announce Type: replace Abstract: Recent advances in large vision-language models have led to impressive performance in visual question answering and multimodal reasoning. However, i
arXiv:2610.04594v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) faithfulness detectors are widely used to audit reasoning models, yet a detector is itself a predictor whose verdicts are treat
arXiv:2610.06666v1 Announce Type: new Abstract: Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer. We argue that an effective latent thought
arXiv:2601.09879v2 Announce Type: replace-cross Abstract: Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report gene
arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to
arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how t
arXiv:2609.38829v1 Announce Type: new Abstract: Multi-path reasoning methods such as self-consistency (SC) sample K reasoning paths and choose the most frequent answer. However, their gains quickly pl
arXiv:2609.38879v1 Announce Type: cross Abstract: Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protei
arXiv:2609.37203v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for natural-language logical reasoning, where the final answer is easy to check but the proof beh
arXiv:2609.37374v1 Announce Type: new Abstract: Reinforcement learning (RL) has recently delivered substantial gains in multimodal reasoning, opening a promising route for fine-grained visual percepti
arXiv:2609.38070v1 Announce Type: new Abstract: As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming incre
arXiv:2609.35942v1 Announce Type: new Abstract: Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs in
arXiv:2609.36126v1 Announce Type: cross Abstract: Modern AI architectures used to solve visual reasoning tasks typically rely heavily on global connectivity and synchronization. As biological systems
arXiv:2609.36653v1 Announce Type: new Abstract: Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with shar
arXiv:2609.32660v1 Announce Type: new Abstract: Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns
arXiv:2609.34682v1 Announce Type: new Abstract: Advances in multimodal understanding, reasoning, and tool use enable agents to tackle increasingly complex visual reasoning tasks. By distilling past ex
arXiv:2609.29496v1 Announce Type: new Abstract: Natural language explanation generation serves as a key mechanism for exposing and evaluating vision-language reasoning. Prior work on explanation-drive
arXiv:2604.01754v2 Announce Type: replace-cross Abstract: Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a cen
arXiv:2609.30192v1 Announce Type: new Abstract: Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises f
arXiv:2609.29664v1 Announce Type: new Abstract: Reinforcement learning (RL) has proven effective in enhancing the reasoning performance of large language models (LLMs), particularly in complex mathema
arXiv:2609.27009v1 Announce Type: new Abstract: Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenge
arXiv:2609.22586v1 Announce Type: cross Abstract: Modern audio-language models are no longer judged only on what words they can transcribe, but on whether they can reason over what they hear: recoveri
arXiv:2609.25773v1 Announce Type: new Abstract: HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes err
arXiv:2603.02266v2 Announce Type: replace-cross Abstract: Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Lan
arXiv:2609.22228v1 Announce Type: new Abstract: Large language models increasingly rely on long chain-of-thought (CoT) trajectories for complex reasoning, but autoregressive generation brings substant
arXiv:2609.22197v1 Announce Type: new Abstract: We study Hierarchical Reasoning Model (HRM), a representative hierarchical Transformer-based latent reasoning model with many variants, on Sudoku, Maze,
arXiv:2603.13099v3 Announce Type: replace Abstract: We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multim
arXiv:2505.23126v5 Announce Type: replace Abstract: Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangl