{"total":57,"rows":[{"id":"2607.26760","title":"Metis: Memory Foundation Model","created":"2026-07-29","cited_by_count":7,"area":"lr"},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2609.04565","title":"Extremely Sparse Supervision Incentivizes Reasoning Ability","created":"2026-09-03","cited_by_count":5,"area":"lr"},{"id":"2609.06746","title":"Reason Through the Latent! Making Latent Visual Reasoning Necessary","created":"2026-09-06","cited_by_count":2,"area":"lr"},{"id":"2607.20327","title":"PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2607.28707","title":"Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.00200","title":"TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.10908","title":"Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences","created":"2026-08-11","cited_by_count":1,"area":"lr"},{"id":"2608.30413","title":"DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2609.17496","title":"Verifiable Social Reasoning for LLM Assistants","created":"2026-09-15","cited_by_count":1,"area":"lr"},{"id":"2609.19991","title":"AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models","created":"2026-09-17","cited_by_count":1,"area":"lr"},{"id":"2608.12585","title":"Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.14927","title":"LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.17895","title":"BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.18011","title":"The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic Reasoning","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.29120","title":"HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.00590","title":"CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.03526","title":"CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.04753","title":"Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.06880","title":"Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.06970","title":"CantoneseLLM v2: Reasoning in a Low-Resource Language","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.11061","title":"Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.12509","title":"ChitraMiti: Benchmarking Visual Grounding and Modality Reliance in Bengali Geometric Reasoning","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.13134","title":"Rethinking Heterogeneous System Disaggregation for Subquadratic Attention","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.15180","title":"Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language Models","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.18677","title":"Voice of Reason: Reinforcement Learning for Spoken Math","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.22878","title":"ISA-Bench: A Benchmark for Computational Reasoning Across Instruction Set Architectures","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.32470","title":"On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32492","title":"Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32569","title":"OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33119","title":"MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34327","title":"Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35673","title":"FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37054","title":"ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38879","title":"Does Learning Protein Folding Generalize to Broader Reasoning?","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.38958","title":"Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39478","title":"Also Small Models Can Reasonably Self-Evaluate Their Confidence","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39846","title":"When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.00296","title":"Certainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.00562","title":"Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.00724","title":"Reason in Style: Discovering and Controlling Style in Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01014","title":"From Discovery to Decision: Finite-Budget Recoverability in LLM Voting","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.01184","title":"ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.01236","title":"Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.01999","title":"From Reasoning Failures to Composable Video Spatial Intelligence","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02819","title":"Text-Centric Post-Training for Omni-Modal Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.04469","title":"Trinity: Self-Evolving Vision-Language Models with a Self-Verifier","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.06366","title":"Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.07469","title":"COMPASS: Finding Where Reasoning Lives in Language Models","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.11810","title":"Seek-and-View Reasoning for Multi-View Spatial Understanding","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12961","title":"MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.18834","title":"Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.18836","title":"Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.20083","title":"VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}