Search: “reasoning”

Enterprise AI adoption at scale requires moving beyond large language models to implement agent logic systems that can handle complex reasoning, planning, and decision-making autonomously. Agent-based

arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmf

arXiv:2509.20941v2 Announce Type: replace Abstract: As surgical AI transitions from pixel-level detection to complex reasoning, Scene Graphs (SGs) offer the structured, relational representations nece

arXiv:2605.30686v1 Announce Type: cross Abstract: ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, a

arXiv:2605.30713v1 Announce Type: cross Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their applicati

arXiv:2605.31228v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models

DeepAgents are AI systems designed to handle complex tasks through advanced reasoning and planning capabilities. The post outlines the key features that enable DeepAgents to excel at complicated probl

NVIDIA Cosmos 3 uses a mixture-of-transformers architecture that pairs a reasoning transformer with a generation transformer, enabling it to understand object interactions and spatial-temporal relatio

arXiv:2605.31370v1 Announce Type: new Abstract: Abductive reasoning over knowledge graphs aims to generate logical hypotheses that explain observed entities or facts. Existing controllable hypothesis

arXiv:2605.31268v1 Announce Type: new Abstract: We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-p

Neurosymbolic rising! I've wanted to work on deep neurosymbolic integration for a while: if you make an 800k transformer reason *like* a logical solver, you get 100% on sudoku-extreme w. 15m of train

arXiv:2605.31558v1 Announce Type: cross Abstract: Transformer-based language models are widespread in today's society. As such, understanding the mechanisms by which they solve structured tasks and pr

arXiv:2511.04393v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as 'agents' for decision-making (DM) in interactive and dynamic environments. Yet, since they

AI agents possess incredible reasoning capabilities and can perform increasingly complex actions. But the reliability of agentic outcomes depends entirely on the quality of the context they can access

arXiv:2602.07864v2 Announce Type: replace Abstract: Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a si

arXiv:2602.03890v2 Announce Type: replace Abstract: Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models

arXiv:2602.23258v2 Announce Type: replace Abstract: While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. C

arXiv:2605.30031v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsaf

arXiv:2509.23571v3 Announce Type: replace-cross Abstract: As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect a

arXiv:2605.29168v1 Announce Type: new Abstract: Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operatio

arXiv:2602.12642v2 Announce Type: replace-cross Abstract: Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation div

arXiv:2605.28866v1 Announce Type: cross Abstract: Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior s

arXiv:2605.30233v1 Announce Type: cross Abstract: Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work inves

arXiv:2601.18395v2 Announce Type: replace Abstract: Document-level Information Extraction (DocIE) aims to produce an output template with the entities, relations, and events of interest occurring in t

arXiv:2512.03109v2 Announce Type: replace-cross Abstract: Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success

arXiv:2605.30136v1 Announce Type: new Abstract: LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to

arXiv:2603.27667v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evide

arXiv:2605.29394v1 Announce Type: new Abstract: While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We

feel very aligned with our vision & Ronak + the awesome Trajectory team’s on practically tackling Continual Learning at scale 🚀 there’s a very good reason why teams are partly building “Observability

fun fact many people don’t know: LLMs actually produce bullshit for many reasons, and would continue to do so (though less) even they weren’t trained on bullshit. legal citation hallucinations are a n

arXiv:2605.29129v1 Announce Type: new Abstract: Agentic AI systems are increasingly being explored as production infrastructure: they reason over multiple steps, call tools, act through workflows, and

arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and inf

arXiv:2605.29198v1 Announce Type: new Abstract: Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including math

arXiv:2605.30058v1 Announce Type: new Abstract: While LLM agents have demonstrated remarkable task-oriented abilities such as planning, reasoning, and action, few works have treated them as complete h

arXiv:2605.28828v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation wh

arXiv:2510.06182v2 Announce Type: replace Abstract: A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might repre

arXiv:2508.15180v3 Announce Type: replace Abstract: High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language

arXiv:2605.29893v1 Announce Type: new Abstract: LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation

arXiv:2603.23853v3 Announce Type: replace Abstract: Combining multiple Vision-Language Models (VLMs) can enhance multimodal reasoning and robustness, but aggregating heterogeneous models' outputs ampl

arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. Thi

arXiv:2605.29712v1 Announce Type: cross Abstract: Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users

arXiv:2605.27785v1 Announce Type: new Abstract: The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it,

arXiv:2605.28313v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arg

arXiv:2605.28465v1 Announce Type: new Abstract: Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generation

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week @every and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check:

arXiv:2602.12586v2 Announce Type: replace Abstract: While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensi