Reasoning papers

Browse recent papers, open the full write-up, or filter the archive by topic.

179 papers found

ReviewPaperPublishedTopics

6.8The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure ModesUnderstanding the reasoning capabilities and limitations of LLMs is crucial for developing more robust and interpretable AI systems.Jun 11, 2026LLM Reasoning Survey

7.5From Consumption to Reflection: Designing Human-AI Relations for Stable ReasoningThis work addresses critical cognitive limitations in AI interactions, potentially improving decision-making processes in applications reliant on LLMs.Jun 11, 2026LLM Reasoning Alignment

6.8Resource-Aware LLM Reasoning for Mobile Edge General IntelligenceThis work is relevant for AI engineers and researchers interested in deploying sophisticated AI reasoning capabilities on edge devices, where computational resources are limited.Jun 11, 2026LLM Reasoning Infra

7.2Multi-Agent Reasoning with Adaptive Worker Allocation for Stance DetectionThis approach could improve the robustness and accuracy of stance detection in complex and nuanced text, which is crucial for applications like sentiment analysis and opinion mining.Jun 11, 2026LLM Agent Reasoning

6.8Are LLMs Bad at Moral Reasoning?Understanding the moral reasoning capabilities of LLMs is crucial for their safe deployment in dynamic environments where ethical considerations are important.Jun 11, 2026LLM Reasoning Evaluation

7.5MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence ReasoningThis work addresses the challenge of effectively utilizing long-tail events in social intelligence tasks, which is crucial for improving AI's understanding of nuanced social interactions.Jun 11, 2026LLM Agent Reasoning

6.8Superficial Beliefs in LLM Decision-MakingUnderstanding the decision-making processes of LLMs is crucial for improving their reliability and interpretability, which is vital for their deployment in real-world applications.Jun 10, 2026LLM Reasoning Interpretability

6.8The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-JudgeUnderstanding the alignment between confidence signals and reasoning quality can improve the evaluation and reliability of multi-agent debate systems, which are crucial for applications requiring complex decision-making and reasoning.Jun 10, 2026LLM Agent Reasoning

6.8Symbolic Reasoning Frameworks Modulate LLM Risk Aversion in Multi-Agent Strategic SettingsUnderstanding how symbolic reasoning frameworks affect language model behavior in strategic settings could inform the design of more effective AI agents in complex environments.Jun 9, 2026LLM Agent Reasoning

6.8Agentic Large Language Models for Automated Structural Analysis of 3D Frame SystemsThis work could streamline the structural analysis process in engineering, reducing manual effort and potentially increasing efficiency and accuracy in 3D frame system evaluations.Jun 8, 2026LLM Agent Reasoning

7.2Don't Make the LLM Read the Graph: Make the Graph ThinkUnderstanding how belief graphs can improve LLM performance in cooperative reasoning tasks could lead to more effective AI systems in complex, multi-agent environments.Jun 8, 2026LLM Agent Reasoning

7.2Lean4Agent: Formal Modeling and Verification for Agent Workflow and TrajectoryFormal verification of agent workflows can enhance the reliability and robustness of AI systems, which is crucial for deploying them in real-world applications.Jun 8, 2026LLM Agent Reasoning

6.8A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical ReasoningUnderstanding the differences between human and AI reasoning can guide the development of more effective AI models that genuinely reason rather than mimic reasoning.Jun 8, 2026LLM Reasoning Evaluation

7.0Memory is Reconstructed, Not Retrieved: Graph Memory for LLM AgentsThis approach could improve the efficiency and accuracy of LLM agents in tasks requiring long-term memory reasoning, potentially reducing computational costs.Jun 6, 2026LLM Agent Reasoning

7.5Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent ReasoningThis research addresses the critical issue of cultural misalignment in LLMs, which is essential for developing AI systems that are sensitive to diverse cultural values and improve decision-making processes.Jun 6, 2026LLM Agent Reasoning

7.2Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI AgentsThis work is relevant for AI engineers and researchers focused on improving the reliability and compliance of AI systems in enterprise settings, addressing key limitations of current LLMs.Jun 6, 2026LLM Agent Reasoning

7.2The Self-Correction Illusion: LLMs Correct Others but Not ThemselvesUnderstanding and addressing the self-correction limitations of LLMs can improve their reliability and performance in real-world applications.Jun 6, 2026LLM Reasoning Evaluation

7.2Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem SolvingImproving the reliability of mathematical reasoning in LLMs can enhance their applicability in complex problem-solving tasks, reducing the need for larger models.Jun 6, 2026LLM Agent Reasoning

7.5NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action ReasoningThis research addresses a critical gap in evaluating AI's normative competence in real-world scenarios, moving beyond simple action selection to deeper reasoning.Jun 5, 2026Agent Reasoning Multimodal

7.5MIRAGE: Mobile Agents with Implicit Reasoning and Generative World ModelsThis work addresses the inefficiencies in mobile agent interactions, potentially streamlining applications that rely on visual and language inputs, which is crucial for real-world deployment.Jun 5, 2026Agent Reasoning Multimodal

7.5FALSIFYBENCH: Evaluating Inductive Reasoning in LLMs with Rule Discovery GamesThis research provides insights into the reasoning capabilities of LLMs, which is crucial for their deployment in scientific tasks and understanding their limitations.Jun 5, 2026LLM Reasoning Evaluation

6.8Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision MakingThis work is relevant for AI researchers and engineers interested in improving the transparency and reliability of decision-making systems that rely on scientific simulations.Jun 5, 2026LLM Reasoning Agent

6.8Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile AgentsThis framework could improve the efficiency and reliability of mobile agents by reducing unnecessary interventions and optimizing resource use, which is crucial for real-time applications.Jun 3, 2026Agent Reasoning Multimodal

6.8Enhancing Operational Safety via Agentic Dialogue Hazard Identification AnalysisImproving hazard identification in safety-critical systems can significantly enhance operational safety, making this research relevant for AI engineers working in high-stakes domains.Jun 3, 2026LLM Agent Reasoning

7.2Inducing Reasoning Primitives from Agent TracesThis approach could improve the efficiency and effectiveness of LLM agents by leveraging learned reasoning patterns, potentially reducing computational costs and enhancing problem-solving capabilities.Jun 3, 2026LLM Agent Reasoning

7.5X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated ProbesUnderstanding LLM reasoning capabilities is crucial for improving model design and ensuring reliable performance in complex tasks.Jun 3, 2026LLM Reasoning Evaluation

7.5Agentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningThis approach addresses the inefficiencies in token usage during reasoning in large language models, providing a mechanism for better control over accuracy and efficiency, which is crucial for practical applications.Jun 3, 2026LLM Agent Reasoning

7.5MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large ModelsThis work addresses critical limitations in current multimodal models, potentially leading to more reliable AI systems capable of complex reasoning tasks.Jun 3, 2026LLM Reasoning Multimodal

7.2Adaptive Latent Agentic ReasoningThis work is relevant for AI researchers and engineers aiming to optimize the performance of LLM agents by reducing unnecessary computational overhead while maintaining decision-making accuracy.Jun 3, 2026LLM Agent Reasoning

6.5Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM AgentsUnderstanding the faithfulness gap in LLM agents is crucial for improving their reliability in applications requiring consistent reasoning and action alignment.Jun 2, 2026LLM Agent Reasoning

7.5Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMsThis work could significantly enhance the performance of reasoning LLMs in diverse tasks, making them more robust and adaptable in real-world applications.Jun 2, 2026LLM Reasoning Alignment

6.8Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market ResolutionImproving oracle accuracy in prediction markets can enhance decision-making processes by providing more reliable forecasts, which is crucial for fields relying on accurate predictions.Jun 1, 2026LLM Agent Reasoning

7.2Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric ReasoningThis work addresses a key limitation of LLMs in interpreting numerical data from simulators, potentially broadening their application in engineering and physics domains.Jun 1, 2026LLM Reasoning Agent

7.2HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMsThis work is relevant for AI researchers and engineers focused on improving the accuracy and efficiency of mathematical reasoning in LLMs, offering a novel approach to combine informal and formal reasoning paradigms.Jun 1, 2026LLM Reasoning Agent

7.5Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model DebateUnderstanding how collective reasoning can improve AI performance has implications for developing more reliable and effective AI systems in various applications.Jun 1, 2026LLM Reasoning Evaluation

7.5Reliable Reasoning with Large Language Models via Preference-Based Maximum SatisfiabilityThis research addresses a significant limitation in LLMs' ability to handle complex optimization tasks, making it relevant for applications in robotics and other constraint-heavy domains.May 29, 2026LLM Reasoning Robotics

6.8Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM AgentsUnderstanding and mitigating incoherence in multi-component LLM systems is crucial for developing reliable AI agents that can handle complex tasks involving multiple interacting components.May 29, 2026LLM Agent Reasoning

6.8Beyond Consensus: Trace-Level Synthesis in Mixture of AgentsThis approach could enhance the accuracy and robustness of AI systems by utilizing diverse reasoning paths, which is crucial for complex problem-solving tasks.May 29, 2026LLM Agent Reasoning

8.5Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy EvaluationUnderstanding how LLMs handle counterfactual reasoning is crucial for their application in real-world policy contexts, where intuitive biases can lead to misinterpretations of complex data.May 29, 2026Benchmark Evaluation LLM

7.5Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt OptimizationThis work addresses a significant challenge in MAS optimization, potentially leading to more efficient and interpretable collaborative AI systems.May 29, 2026LLM Agent Reasoning

7.0MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMsUnderstanding and improving the social and strategic reasoning of LLMs is crucial for their deployment in real-world multi-agent scenarios, making this evaluation platform a valuable tool for researchers and developers.May 29, 2026LLM Agent Reasoning

6.8Revealing Algorithmic Deductive Circuits for Logical ReasoningUnderstanding the internal mechanisms of LLMs in logical reasoning can enhance model interpretability and guide the development of more efficient reasoning systems.May 28, 2026LLM Reasoning Interpretability

7.5LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal ReasoningThis framework addresses critical challenges in legal AI by ensuring transparency and reliability in legal judgments, which is essential for practitioners and researchers in the field.May 28, 2026Agent Reasoning

7.5Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial ReasoningImproving LLMs' spatial reasoning capabilities is crucial for their application in real-world scenarios, particularly in embodied intelligence tasks.May 28, 2026LLM Reasoning Agent

7.0Verifiable Process Rewards for Agentic ReasoningThis approach could significantly improve the reasoning capabilities of AI systems by providing more precise feedback, which is crucial for developing more reliable and intelligent agents.May 28, 2026LLM Agent Reasoning

6.8Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential PlanningUnderstanding depth allocation in LLMs for agentic tasks can enhance the design of more efficient and effective autonomous agents.May 28, 2026LLM Agent Reasoning

7.0An LLM-Based Assistance System for Intuitive and Flexible Capability-Based PlanningThis work is relevant for AI engineers and researchers interested in enhancing the flexibility and user-friendliness of automated planning systems in dynamic industrial environments.May 28, 2026LLM Agent Reasoning

7.2MolLingo: Molecule-Native Representations for LLM-Powered Scientific AgentsThis work is relevant for AI researchers and engineers interested in leveraging LLMs for complex scientific tasks, particularly in molecular design and drug discovery.May 28, 2026LLM Agent Reasoning

7.2Integrated and Cross-Architecture Interpretation of LLM ReasoningUnderstanding LLM reasoning is crucial for improving model transparency and trustworthiness, which are essential for real-world applications.May 28, 2026LLM Reasoning Interpretability

7.0Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded ReasoningUnderstanding and improving the sensitivity of legal AI to relevant legal changes is crucial for developing trustworthy systems that can be relied upon in judicial contexts.May 27, 2026LLM Reasoning Evaluation