{"total":28,"rows":[{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2601.12307","title":"Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline","created":"2026-01-18","cited_by_count":22,"area":"lr"},{"id":"2510.12171","title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science","created":"2025-10-14","cited_by_count":15,"area":"lr"},{"id":"2601.15625","title":"Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors","created":"2026-01-22","cited_by_count":10,"area":"lr"},{"id":"2511.06221","title":"Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B","created":"2025-11-09","cited_by_count":8,"area":"lr"},{"id":"2512.13159","title":"SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning","created":"2025-12-15","cited_by_count":8,"area":"lr"},{"id":"2601.04055","title":"Modular Prompt Optimization: Optimizing Structured Prompts with Section-Local Textual Gradients","created":"2026-01-07","cited_by_count":8,"area":"lr"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2510.22087","title":"QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture","created":"2025-10-24","cited_by_count":3,"area":"lr"},{"id":"2508.11386","title":"Retrieval-augmented reasoning with lean language models","created":"2025-08-15","cited_by_count":2,"area":"lr"},{"id":"2508.18091","title":"Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization","created":"2025-08-25","cited_by_count":1,"area":"lr"},{"id":"2510.13935","title":"Big Reasoning with Small Models: Instruction Retrieval at Inference Time","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"id":"2601.07790","title":"Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2605.18380","title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2607.19395","title":"From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2508.12198","title":"Exploring Multimodal AI Reasoning for Meteorological Forecasting from Skew-T Diagrams","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2510.01428","title":"BioVERSE: Representation Alignment of Biomedical Modalities to LLMs for Multi-Modal Reasoning","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2511.16073","title":"Mathematical Framework for Custom Reward Functions in Job Application Evaluation using Reinforcement Learning","created":"2025-11-20","cited_by_count":0,"area":"lr"},{"id":"2601.23085","title":"OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2606.00683","title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2607.14149","title":"Enhancing Small Language Models Reasoning through Knowledge Graph Grounding","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2608.13420","title":"Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.22472","title":"Small Reasoning Models are Instruction Followers in Function Calling","created":"2026-08-23","cited_by_count":0,"area":"lr"},{"id":"2609.17848","title":"SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}