{"total":65,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2410.07163","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","created":"2024-10-09","cited_by_count":172,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"id":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2505.15214","title":"R-TOFU: Unlearning in Large Reasoning Models","created":"2025-05-21","cited_by_count":9,"area":"lr"},{"id":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"id":"2412.03467","title":"Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning","created":"2024-12-04","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2511.01170","title":"DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models","created":"2025-11-03","cited_by_count":5,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2502.04030","title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","created":"2025-02-06","cited_by_count":4,"area":"lr"},{"id":"2509.01363","title":"Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic","created":"2025-09-01","cited_by_count":4,"area":"lr"},{"id":"2510.00579","title":"CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs","created":"2025-10-01","cited_by_count":4,"area":"lr"},{"id":"2602.05805","title":"NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2505.16151","title":"Training-Free Reasoning and Reflection in MLLMs","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2505.22635","title":"Learning Composable Chains-of-Thought","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2508.15507","title":"Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2510.06052","title":"MixReasoning: Switching Modes to Think","created":"2025-10-07","cited_by_count":3,"area":"lr"},{"id":"2510.08987","title":"Towards Efficient Multimodal Unified Reasoning Model via Model Merging","created":"2025-10-10","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":"2605.21468","title":"You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories","created":"2026-05-20","cited_by_count":3,"area":"lr"},{"id":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2504.01789","title":"OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models","created":"2025-04-02","cited_by_count":2,"area":"lr"},{"id":"2505.19075","title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2512.07710","title":"Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2601.13992","title":"\"The Whole Is Greater Than the Sum of Its Parts\": A Compatibility-Aware Multi-Teacher CoT Distillation Framework","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2604.00716","title":"CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2607.15587","title":"Rethinking Transfer in Continual Learning: A Replay-Based Realisation","created":"2026-07-17","cited_by_count":1,"area":"lr"},{"id":"2607.18026","title":"Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2608.05541","title":"Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging","created":"2026-08-06","cited_by_count":1,"area":"lr"},{"id":"2510.17598","title":"Reasoning Distillation and Structural Alignment for Improved Code Generation","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2603.21705","title":"Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2604.06465","title":"Multi-objective Evolutionary Merging Enables Efficient Reasoning Models","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2605.14386","title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.01080","title":"ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2607.14895","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2608.04519","title":"Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.10447","title":"Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.14465","title":"You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.28859","title":"The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2608.29623","title":"MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.31140","title":"Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.34344","title":"Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35347","title":"Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.05219","title":"Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.08659","title":"Selective Transfer of RL Updates for Visual Reasoning","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}