Knowledge catalogue
arXiv:2603.18859v2 Announce Type: replace Abstract: Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process
arXiv:2605.30290v1 Announce Type: cross Abstract: Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verifica
arXiv:2602.15382v2 Announce Type: replace Abstract: Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete
arXiv:2605.30161v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D und
arXiv:2603.26182v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required fo
arXiv:2512.23959v3 Announce Type: replace-cross Abstract: Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that
arXiv:2502.12468v2 Announce Type: replace-cross Abstract: The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as pr
arXiv:2604.18530v2 Announce Type: replace Abstract: Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have significantly improved Large Language Model (LLM) reasoning, yet m
arXiv:2605.27709v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evalu
arXiv:2505.13820v5 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-sty
arXiv:2605.28295v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the po
arXiv:2605.27311v1 Announce Type: new Abstract: Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions t
arXiv:2605.26827v1 Announce Type: cross Abstract: Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextua
arXiv:2603.21563v2 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such s
arXiv:2605.26835v1 Announce Type: new Abstract: LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search
arXiv:2605.26874v1 Announce Type: cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes
arXiv:2605.26399v1 Announce Type: new Abstract: Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typ
this is a fantastic example of a robust agentic memory system built on langgraph! there's 4 key parts 1. retrieval (rag) 2. storage, fragmented by memory type 3. reasoning* 4. learning (often called d
arXiv:2605.25549v1 Announce Type: cross Abstract: High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production m
arXiv:2605.25143v1 Announce Type: new Abstract: Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories. The key challenge is to ma
arXiv:2605.25393v1 Announce Type: new Abstract: Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning
arXiv:2605.25198v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but i
arXiv:2505.23764v3 Announce Type: replace-cross Abstract: Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, h
arXiv:2602.10635v2 Announce Type: replace Abstract: Socially intelligent AI systems must entail reasoning across diverse human behavioral tasks, and generalization to new contexts. However, AI has yet
arXiv:2603.09095v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided a
arXiv:2605.25534v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term th
arXiv:2605.23972v1 Announce Type: new Abstract: Large language models achieve strong performance in language generation and knowledge-intensive tasks, yet remain limited in settings requiring causal r
Dropped this morning by the Vatican: Magnifica Humanitas of His Holiness Pope Leo XIV on Safeguarding the Human Person in the Time of Artificial Intelligence. This is a very interesting document. It's
arXiv:2605.22875v1 Announce Type: new Abstract: We present extbf{Research Math Agents (RMA)}, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies
arXiv:2603.02938v2 Announce Type: replace Abstract: Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Network
arXiv:2605.21931v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, e
NuExtract3 is a unified 4B vision-language reasoning model for document understanding that combines structured information extraction with image-to-Markdown conversion, suitable for OCR and RAG prepro
arXiv:2605.20423v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on many language tasks, but their Theory of Mind (ToM) reasoning is still uneven in complex social settings. E
arXiv:2605.22109v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchm
arXiv:2605.21781v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for
arXiv:2605.22536v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pr
arXiv:2601.10348v2 Announce Type: replace Abstract: Efficient distillation is a key pathway for converting expensive reasoning capability into deployable efficiency, yet in the frontier regime where t
arXiv:2602.06511v3 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but design
arXiv:2605.20682v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot unders
arXiv:2605.20033v1 Announce Type: new Abstract: Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approache
arXiv:2605.18780v1 Announce Type: cross Abstract: Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of thei
arXiv:2506.07209v2 Announce Type: replace-cross Abstract: We present HOI-PAGE, a new approach that prioritizes part-level affordance reasoning to generate high-fidelity 4D human-object interactions (H
arXiv:2605.18843v1 Announce Type: new Abstract: Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet mod
arXiv:2605.19196v1 Announce Type: new Abstract: Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, an
arXiv:2605.18194v1 Announce Type: new Abstract: While Multi-Modal Large Language Models (MLLMs) demonstrate impressive capabilities in general reasoning, their embodied spatial intelligence remains ha
arXiv:2605.17450v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for automated vulnerability repair (AVR), where repository-level reasoning enables them to ins
arXiv:2508.08501v3 Announce Type: replace Abstract: We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built
arXiv:2605.18556v1 Announce Type: cross Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, curre
arXiv:2508.15878v2 Announce Type: replace-cross Abstract: Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling
arXiv:2601.01685v2 Announce Type: replace-cross Abstract: As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an
arXiv:2605.18176v1 Announce Type: cross Abstract: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participa
arXiv:2605.16460v1 Announce Type: new Abstract: Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorp
arXiv:2512.22471v5 Announce Type: replace-cross Abstract: Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analy
arXiv:2605.16787v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the le
arXiv:2605.15529v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Down
arXiv:2605.15016v1 Announce Type: cross Abstract: As large language models empower healthcare, intelligent clinical decision support has developed rapidly. Longitudinal electronic health records (EHR)
arXiv:2509.14232v5 Announce Type: replace Abstract: Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style bench
arXiv:2605.15113v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning
arXiv:2601.19924v2 Announce Type: replace-cross Abstract: We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reason
arXiv:2605.14558v1 Announce Type: cross Abstract: Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment