{"total":52,"rows":[{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2505.13308","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","created":"2025-05-19","cited_by_count":43,"area":"lr"},{"id":"2402.17887","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","created":"2024-02-27","cited_by_count":32,"area":"lr"},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2507.05418","title":"Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning","created":"2025-07-07","cited_by_count":24,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2503.05212","title":"Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning","created":"2025-03-07","cited_by_count":16,"area":"lr"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2506.10822","title":"ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization","created":"2025-06-12","cited_by_count":14,"area":"lr"},{"id":"2502.00997","title":"MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs","created":"2025-02-03","cited_by_count":13,"area":"lr"},{"id":"2502.11740","title":"Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent","created":"2025-02-17","cited_by_count":13,"area":"lr"},{"id":"2410.23703","title":"OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models","created":"2024-10-31","cited_by_count":12,"area":"lr"},{"id":"2505.20196","title":"Temporal Sampling for Forgotten Reasoning in LLMs","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2508.12281","title":"Legal$\\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain","created":"2025-08-17","cited_by_count":12,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2410.16930","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2509.23629","title":"Emergent Slow Thinking in LLMs as Inverse Tree Freezing","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2503.09620","title":"Exploiting Edited Large Language Models as General Scientific Optimizers","created":"2025-03-08","cited_by_count":7,"area":"lr"},{"id":"2506.22920","title":"Improving Rationality in the Reasoning Process of Language Models through Self-playing Game","created":"2025-06-28","cited_by_count":7,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2502.09042","title":"Typhoon T1: An Open Thai Reasoning Model","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2505.20643","title":"Can Past Experience Accelerate LLM Reasoning?","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2505.22131","title":"Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2508.17803","title":"DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models","created":"2025-08-25","cited_by_count":3,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2312.07886","title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","created":"2023-12-13","cited_by_count":2,"area":"lr"},{"id":"2508.08275","title":"MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","cited_by_count":2,"area":"lr"},{"id":"2511.15375","title":"Parameter Importance-Driven Continual Learning for Foundation Models","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"id":"2407.11780","title":"SwitchCIT: Switching for Continual Instruction Tuning","created":"2024-07-16","cited_by_count":1,"area":"lr"},{"id":"2512.16914","title":"Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates","created":"2025-12-18","cited_by_count":1,"area":"lr"},{"id":"2601.21894","title":"Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.20162","title":"Talking to Yourself: Defying Forgetting in Large Language Models","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2603.02504","title":"NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cocktail Effect","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2603.26330","title":"Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2607.20553","title":"CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2608.11758","title":"AWARe: Mitigating Catastrophic Forgetting via Activation-Weighted Adaptive REtention","created":"2026-08-12","cited_by_count":1,"area":"lr"},{"id":"2505.00017","title":"ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation","created":"2025-04-24","cited_by_count":0,"area":"lr"},{"id":"2505.11893","title":"RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving","created":"2025-05-17","cited_by_count":0,"area":"lr"},{"id":"2507.16971","title":"Text-to-SPARQL Goes Beyond English: Multilingual Question Answering Over Knowledge Graphs through Human-Inspired Reasoning","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2605.10120","title":"MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2607.03166","title":"KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2608.05151","title":"Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2609.04489","title":"Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2610.05200","title":"Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}