{"total":44,"rows":[{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2505.12448","title":"SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning","created":"2025-05-18","cited_by_count":46,"area":"lr"},{"id":"2509.23040","title":"Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents","created":"2025-09-27","cited_by_count":38,"area":"lr"},{"id":"2509.24765","title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","created":"2025-09-29","cited_by_count":32,"area":"lr"},{"id":"2601.02902","title":"Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning","created":"2026-01-06","cited_by_count":25,"area":"lr"},{"id":"2601.07408","title":"Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning","created":"2026-01-12","cited_by_count":19,"area":"lr"},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2504.06214","title":"From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models","created":"2025-04-08","cited_by_count":14,"area":"lr"},{"id":"2505.24164","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2510.16476","title":"NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems","created":"2025-10-18","cited_by_count":11,"area":"lr"},{"id":"2508.04852","title":"VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence","created":"2025-08-06","cited_by_count":9,"area":"lr"},{"id":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2505.07313","title":"Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study","created":"2025-05-12","cited_by_count":8,"area":"lr"},{"id":"2505.12833","title":"Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs","created":"2025-05-19","cited_by_count":8,"area":"lr"},{"id":"2505.16368","title":"SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2601.14952","title":"CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2601.18204","title":"MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning","created":"2026-01-26","cited_by_count":7,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4,"area":"lr"},{"id":"2509.23291","title":"Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces","created":"2025-09-27","cited_by_count":4,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2602.12056","title":"LawThinker: A Deep Research Legal Agent in Dynamic Environments","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2504.18587","title":"An Expectation-Maximization Perspective on Reinforcement Learning for LLM Reasoning","created":"2025-04-24","cited_by_count":3,"area":"lr"},{"id":"2508.10967","title":"Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2608.15962","title":"SEER: Long-Context Reasoning via Selective Visual-Text Compression","created":"2026-08-16","cited_by_count":3,"area":"lr"},{"id":"2502.13753","title":"SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning","created":"2025-02-19","cited_by_count":1,"area":"lr"},{"id":"2508.03622","title":"Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2509.21028","title":"SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific Articles","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2510.09227","title":"RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.11996","title":"Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning","created":"2025-10-13","cited_by_count":1,"area":"lr"},{"id":"2510.13095","title":"Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"id":"2601.17842","title":"EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapy","created":"2026-01-25","cited_by_count":1,"area":"lr"},{"id":"2603.05400","title":"An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2603.15417","title":"Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2607.21933","title":"Semiotic logical hexagon theory for LLM logical reasoning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2508.11808","title":"Labels or Input? Rethinking Augmentation in Multimodal Hate Detection","created":"2025-08-15","cited_by_count":0,"area":"lr"},{"id":"2604.20983","title":"Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2608.03048","title":"PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory","created":"2026-08-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}