ACL 2026 — Reasoning & Theorem Proving | Rajat Kanti Bhattacharjee

Reasoning & Theorem Proving

448 papers Links not yet available — ACL proceedings pending on ACL Anthology.

OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning
Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
Benchmarking LLM’s Capability in Reasoning over Conflicting Web References
SLR: Automated Synthesis for Scalable Logical Reasoning
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models
Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning
ImReasoner: Improving Memory-based Language Models for Reasoning-in-a-Haystack Tasks
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
Logic Matters in Lightweight Hallucination Classification for RAG System
Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering
Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization
ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
OneRec-Think: In-Text Reasoning for Generative Recommendation
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
LEASH: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
Optimizing Length Compression in Large Reasoning Models
Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics
COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination
Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models
RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains
D²Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning
Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models
Miner: Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
Reasoning Structure Matters for Safety Alignment of Reasoning Models
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning
Visually-Guided Policy Optimization for Multimodal Reasoning
From “Aha Moments” to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control
Metaphor Reasoning is Meta-reasoning
SeLaR: Selective Latent Reasoning in Large Language Models
STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors
MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning
Beyond Timestamps: Bridging Forward and Backward Reasoning in Temporal Numerical and Relational Understanding
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
VideoPro: Adaptive Program Reasoning for Long Video Understanding
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios
Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations
ReportLogic: Evaluating Logical Quality in Deep Research Reports
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
Revisiting Model Interpolation for Efficient Reasoning
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning
From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level
Dissecting Failure Dynamics in Large Language Model Reasoning
Visual Attention Reasoning via Hierarchical Search and Self-Verification
LearnerCoMPASS: Intelligent Tutoring System with Dynamic Cognitive Diagnosis and Multi-Model Path Planning
KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments
Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning
PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition
MuSe: Multi-Stage Graph Reasoning via Vision-Language Models
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding
Unified Thinker: A General Reasoning Core for Image Generation
Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text
Reasoning with Ontology Graph: Toward Type-Constrained Knowledge Graph Question Answering
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
ProgressLM: Towards Progress Reasoning in Vision-Language Models
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Why Do Emotions Change? Appraisal-Guided Reasoning for Emotion–Cause Triplet Extraction in Conversations
MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
Reasoning Gets Harder for LLMs Inside A Dialogue
Deriving Character Logic from Storyline as Codified Decision Trees
From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection
UR²: Unify RAG and Reasoning through Reinforcement Learning
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning
Interleaved Tool-Call Reasoning for Protein Function Understanding
GLARE: Agentic Reasoning for Legal Judgment Prediction
Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents
How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them
From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing
Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
Reliable Use of Lemmas via Eligibility Reasoning and Section‑Aware Reinforcement Learning
MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics
MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs
BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs
The Path Not Taken: Duality in Reasoning about Program Execution
APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering
From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning
LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning
Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks
Model-Based Imaginative Planning for Embodied Agents
Semantic-Aware Logical Reasoning via a Semiotic Framework
Calibration-Aware Policy Optimization for Reasoning LLMs
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
Closing the Modality Reasoning Gap for Speech Large Language Models
Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
ODL-TempLLM: Ontology-Guided and Description Logic-Reasoned Temporal Reasoning with LLMs
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering
RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play
HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
Merlin’s Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
ReEfBench: Quantifying the Reasoning Efficiency of LLMs
Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning
THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning
GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
Controllable LLM Reasoning via Sparse Autoencoder‑Based Steering
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation
Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
MAGIC: Deep Geometric Evolution with Structural Consensus for Temporal Knowledge Graph Reasoning
Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts
MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents
IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement
EpiCaR: Knowing What You Don’t Know Matters for Better Reasoning in LLMs
Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
Red Teaming Large Reasoning Models
InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
CamoQuery: Language-Guided Reasoning Camouflaged Object Segmentation
Make LLMs See Like Investigators, Not Just Think More: The Role of Structured Analysis in Investigative Reasoning
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
PEAP: Proactive Embodied Action Sequence Planning with Joint Understanding of Vision and Audio Perception
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
Are they lovers or friends? Evaluating LLMs’ Social Reasoning in English and Korean Dialogues
When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
LegalChainReasoner: Grounding Criminal Judicial Opinion Generation via Structured Legal Chains
Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models
AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
Agentic Oversight via Dialectic Reasoning
Agent Newsroom: Efficient Chronological Report Generation via Dynamic Multi-Agent Collaboration
MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning
From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion
CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
Reasoning Fails Where Step Flow Breaks
Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents
MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
Data Pollination: An Emergent Ecological Process Driving AI Population Evolution
Extending First-Order Logic for Factual Reasoning over Knowledge Graphs
Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry
Achieving Multi-Hop Calculation and Safe Abstention in Financial Numerical Reasoning by Metric Graph Constrained LLMs
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables
OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
Temporal Sampling for Forgotten Reasoning in LLMs
Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks
DIXITWORLD: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
Think before Go: Hierarchical Reasoning for Image-goal Navigation
CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models
Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models
Communicating in Emergent Language with an Induced Morphological Phrasebook
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning
Beyond the Panorama: Training-Free Hierarchical Perception-Reasoning for Fine-Grained Vision in MLLMs
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
Do LLMs Encode Functional Importance of Reasoning Tokens ?
EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning
ReCreate: Reasoning and Creating Domain Agents Driven by Experience
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection
A Survey of Inductive Reasoning for Large Language Models
Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision
SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection
Injecting Context via Situation Working Memory for Logical Reasoning with LLMs
Quantifying and Understanding Uncertainty in Large Reasoning Models
The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models
Enhanced Reasoning for Biomedical Document-Level Relation Extraction via a Novel Cascade Language Model Framework
Synthetic Data Generation for Training Diversified Commonsense Reasoning Models
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry
How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
Ranking Reasoning LLMs under Test-Time Scaling
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning
SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models
TPS-Bench: Evaluating AI Agents’ Tool Planning & Scheduling Abilities in Compounding Tasks
CityVG: Contrastive Fine-Tuning and Reward-Based Chain-of-Thought Reasoning for Zero-Shot City-Scale 3D Visual Grounding
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
SMART: Evaluating LLMs’ Mathematical Reasoning via a Human Cognitive Process-Inspired Benchmark
HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
CʜAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs
An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal
Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio
Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis
VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning
Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
Adaptive Retrieval for Reasoning
On Emergent Social World Models — Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
TH-RAG : Topic-Based Hierarchical Knowledge Graphs for Robust Multi-hop Reasoning in Graph-based RAG Systems
R³: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning
Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA
MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision
Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
Foresight Optimization for Strategic Reasoning in Large Language Models
CheckRLM: Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented Reasoning
FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner
Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing
ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following
ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
JoPR: Joint Emotion Perception and Reasoning for Conversational Emotion Recognition
Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression
Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning
On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning
Figure It Out: Improve the Frontier of Reasoning with Executable Visual States
NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
AttnPO: Attention-Guided Process Supervision for Efficient Reasoning
Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression
Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process
AdaMix: Adaptive Mixing for Short and Long Reasoning Adapters
UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning
E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence
GROKE: Vision-Free Navigation Instruction Evaluation via Graph Reasoning on OpenStreetMap
LongVideoAgent: Multi-Agent Reasoning with Long Videos
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning
GeoRC: A Benchmark for Geolocation Reasoning Chains
Thinking in Schemas: Robust Syllogistic Reasoning in LLMs
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
Social Story Frames: Contextual Reasoning about Narrative Intent and Reception
A Survey of Reasoning-Intensive Retrieval: Progress and Challenges
LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models
PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning
A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
EDUMATH: Generating Standards-aligned Educational Math Word Problems
Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning
Reasoning Traces Shape Outputs but Models Won’t Say So
AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception
From Trajectories to Graphs: Contract-Checked Editing for Verifier-Guided LLM Reasoning
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
Knowledge Vector of Logical Reasoning in Large Language Models
SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
Programming over Thinking: Efficient and Robust Multi-Constraint Planning
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
ParaSuite: Boosting LLM Reasoning via Paradox Resolution
rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection
AIPO: Adaptive Information Guided Token-Level Reinforcement Learning for Large Language Model Reasoning
DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference
Benchmarking Fine-Grained Error Detection in Multimodal Reasoning
Parallel Test-Time Scaling for Latent Reasoning Models
SciMDR: Advancing Scientific Multimodal Document Reasoning
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
TInR: Exploring Tool-Internalized Reasoning in Large Language Models
How Long Reasoning Chains Influence LLMs’ Judgment of Answer Factuality
MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models
Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA
Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment
Minimal Free Resolution Guided Adaptive Tree Reasoning
Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations
Monotonic Scaffolding as a Diagnostic Lens for Legal Reasoning in LLMs
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning
Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings
ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks
MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?
REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation
ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling
Reinforced Efficient Reasoning via Semantically Diverse Exploration
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures