60 stories tagged with #reasoning, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Reasoning"
The crossway of moral reasoning and cultural growth in today's globe
The crossway of moral reasoning and cultural growth in today's globe…
Opus 5 improves coding, reasoning efficiency, and prompt-cache-friendly tool use, and is priced at $5/1M input tokens and $25/1M output, same as Opus 4.8 (David Gewirtz/ZDNET)
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607.19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context leng…
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: …
On Locality and Length Generalization in Visual Reasoning
A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes…
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constr…
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typicall…
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv:2607.09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly struc…
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv:2607.09059v1 Announce Type: new Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints…
MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
arXiv:2606.27652v1 Announce Type: new Abstract: We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even thoug…
GPT-5.6 Sol matches Mythos Preview on ExploitBench, adds Ultra mode with subagents for complex workflows, and max reasoning for deep problem-solving (OpenAI)
OpenAI : GPT-5.6 Sol matches Mythos Preview on ExploitBench, adds Ultra mode with subagents for complex workflows, and max reasoning for deep problem-solving — We're beginning a li…
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Trac
Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning task…
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
arXiv:2606.26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with…
When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning
Long-horizon reasoning requires a system to commit to medium-horizon intent without becoming rigid: re-plan too often and computation never coheres into multi-step structure; commi…
Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
The do-calculus defines a general system of inference for interventional queries, allowing causal quantities to be transformed through successive applications of its rules. This pr…
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frame…
From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models
Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical failure mode: a model may o…
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs…
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions, either by failing to satisfy…
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoT…
CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstr…
Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents
Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide \emph{when} to in…
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. …
CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability. Existing detection m…
Inducing Reasoning Primitives from Agent Traces
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Ind…
Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models
Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assumption that longer reasoning…
ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning
Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic…
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time. In this paper, we …
Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
A Blog post by NVIDIA on Hugging Face…
Claude Does Not Need More Prompts. It Needs Reasoning Discipline.
Large language models are good at sounding structured. That is not the same as being structured. Ask...…
The Evil of corporate America and their reasoning skills is that of people who enter a building to find the exit.
Gryphe/Pantheon-Reasoning-27B · Hugging Face
My Stepmom Won’t Come to My House to See My Baby. Her Reasoning Is Not Normal.
This cannot be healthy.…
Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding
Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead an…
Fooling around with encrypted reasoning blobs
This is a quick post I wanted to write about a “hobby project” I spent a weekend on. It has little to do with real cryptography, and mostly doesn’t expose a particularly exciting ……
AutoTTS reduces token usage by 69.5% in LLM reasoning strategies
AutoTTS, a framework from Meta, Google, and university researchers, cuts LLM token usage by 69.5% while maintaining accuracy, with implications for AI-driven crypto tools.…
Researchers automated LLM reasoning strategy design and cut token usage by 69.5%
I gave my AI agents email instead of better reasoning. They started fixing each other's bugs.
What's the reasoning behind not letting us download our entire SMS messages as easy as possible?
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue …
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
Vision-Language Models (VLMs) have shown rapid progress in mobile GUI navigation. This paper presents a systematic study of data scaling, benchmarking, and reasoning for VLM-based …
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficult to integrate process, poll…
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly…
MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning
Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, and recommendation rules. Howe…
Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning
Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations, but should change when per…
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like diffe…
5.5/5.4 Reasoning Cheatsheet (YMMV)
Verbosity is not faithfulness: an architectural argument that reasoning models cannot perform faithful inference [D]
What Sudoku reveals about the limits of LLMs
LLM failure to solve reasoning puzzles exposes deep architectural limits…
Show HN: skills-for-humanity – 171 structured reasoning skills for Claude Code
Structured reasoning methodologies from history's most rigorous thinkers, packaged as Claude Code skills. - human-avatar/skills-for-humanity…
Credit Assignment with Resets in Language Model Reasoning
Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…
Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis
While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and…
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories …
Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning
Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TAGs). This work reframes CoT-…
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evolution, current AI in Earth scie…
Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework
LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into th…
GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration
While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplore…
PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models
Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously ac…
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their e…
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In cont…