Knowledge catalogue
arXiv:2601.00791v2 Announce Type: replace-cross Abstract: Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and ou
arXiv:2603.09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentia
arXiv:2606.04806v1 Announce Type: cross Abstract: LLMs and agentic systems are increasingly deployed in social environments, making normative competence critical for safe and appropriate behavior. How
arXiv:2606.04505v1 Announce Type: new Abstract: Scientific simulators are increasingly being integrated into LLM-driven systems for high-stakes simulation-driven decision-making. However, existing fra
Nice primer on post-training reasoning data. (bookmark it) This is one of the first primers to pull the scattered post-training reasoning-data literature into one place, synthesizing over 150 public s
arXiv:2606.02465v1 Announce Type: cross Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, lar
arXiv:2605.31378v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs
arXiv:2605.22074v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard p
arXiv:2605.19762v1 Announce Type: new Abstract: Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the
arXiv:2512.07461v3 Announce Type: replace Abstract: We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reas
arXiv:2506.13351v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality refer
arXiv:2605.03460v1 Announce Type: cross Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which
arXiv:2604.22074v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes.
arXiv:2510.21285v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harm
arXiv:2604.21584v1 Announce Type: new Abstract: Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a tar
arXiv:2604.08016v2 Announce Type: replace Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an
arXiv:2604.20328v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, a
arXiv:2604.19656v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are
arXiv:2602.11675v3 Announce Type: replace Abstract: Large language models may answer causal questions correctly for the wrong reasons, substituting associational shortcuts P(Y|X) for the interventiona
arXiv:2510.00546v5 Announce Type: replace Abstract: Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics,
arXiv:2511.11113v2 Announce Type: replace Abstract: Reinforcement fine-tuning (RFT), a two-stage framework consisting of supervised fine-tuning (SFT) and reinforcement learning (RL) has shown promisin
arXiv:2508.10164v2 Announce Type: replace Abstract: Recent advances in Large Reasoning Models (LRMs) have demonstrated strong performance on complex tasks through long Chain-of-Thought (CoT) reasoning
Anthropic says Opus 4.7 hits 80.6% on Document Reasoning — up from 57.1%. But 'reasoning about documents' ≠ 'parsing documents for agents.' We ran it on ParseBench. → Charts: 13.5% → 55.8% (+42.3) — h
arXiv:2604.13395v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LR
arXiv:2603.21440v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) demonstrate impressive natural language capabilities but often struggle with knowledge-intensive reasoning tasks.
arXiv:2602.10042v3 Announce Type: replace-cross Abstract: Recent studies have demonstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability
arXiv:2604.10228v1 Announce Type: new Abstract: Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this
arXiv:2604.09167v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance in multimodal understanding and reasoning, yet grounded reasoning in 3D scenes remains un
arXiv:2610.16598v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning enables multimodal large reasoning models (MLRMs) to solve complex visual problems, but also exposes them to CoT hijack
arXiv:2610.15565v1 Announce Type: new Abstract: Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchm
arXiv:2610.10996v1 Announce Type: new Abstract: Latent reasoning models repeatedly update a latent state using the same recurrent block. As the recurrent depth increases, the sequence of latent states
arXiv:2610.12061v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks. They typically perform reasoning before each action thro
arXiv:2610.09186v1 Announce Type: new Abstract: We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when
arXiv:2610.04188v2 Announce Type: replace Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In t
arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable re
arXiv:2609.27038v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfu
arXiv:2609.27041v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning ap
arXiv:2609.21675v1 Announce Type: new Abstract: Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural-
arXiv:2609.20846v1 Announce Type: new Abstract: While modern large reasoning models (LRMs) excel at providing correct answers in many tasks, we provide additional evidence for the observation that the
arXiv:2609.18736v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), performing logically consistent deductive reasoning over extended interactions remains challeng
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribute
arXiv:2510.15987v3 Announce Type: replace Abstract: How do inference time and latent computations enable large language models (LLMs) to solve multi-step reasoning problems? We introduce AlgoTrace, a
arXiv:2608.25542v1 Announce Type: cross Abstract: Large reasoning models often produce reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established resu
arXiv:2608.24232v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) generate intermediate reasoning traces that may contain unsafe content, even when their final responses appear safe. Guard
arXiv:2504.09772v3 Announce Type: replace Abstract: Test-Time Scaling has emerged as a powerful method to extend the reasoning capabilities of Large Language Models. However, single-agent TTS faces si
arXiv:2608.17443v1 Announce Type: new Abstract: Knowledge Graph Reasoning (KGR) aims to discover latent facts by leveraging the structural evidence available in KGs, posing a challenge to the structur
Yesteday a paper showed a gap that allows to see 100% of the reasoning tokens form ALL Claude and GPT models Stealing Reasoning Traces from Proprietary LLM APIs. check it out, they have published lots
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predi
arXiv:2608.02585v1 Announce Type: cross Abstract: Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping
arXiv:2601.03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (eg backtracking, cross-verification) during the reasoning process,
arXiv:2607.20902v1 Announce Type: cross Abstract: Goal reasoning in Non-Axiomatic Logic (NAL) explains how an adaptive system derives means for realizing desired events under insufficient knowledge an
arXiv:2601.08010v3 Announce Type: replace Abstract: Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasonin
arXiv:2607.00862v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequ
arXiv:2607.00485v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reas
arXiv:2606.31645v1 Announce Type: new Abstract: Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpati
arXiv:2606.29150v1 Announce Type: new Abstract: Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks
arXiv:2606.29164v1 Announce Type: cross Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains
arXiv:2606.15753v2 Announce Type: replace Abstract: Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding th
arXiv:2506.07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, th
arXiv:2606.19120v2 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned