{"total":97,"rows":[{"id":"2509.21500","title":"Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training","created":"2025-09-25","cited_by_count":53,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2510.23038","title":"Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2505.21825","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2507.12399","title":"ROC-n-reroll: How verifier imperfection affects test-time scaling","created":"2025-07-16","cited_by_count":12,"area":"lr"},{"id":"2506.04118","title":"Guided Speculative Inference for Efficient Test-Time Alignment of LLMs","created":"2025-06-04","cited_by_count":11,"area":"alignment"},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","cited_by_count":9,"area":"alignment"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2510.15464","title":"Learning to Answer from Correct Demonstrations","created":"2025-10-17","cited_by_count":7,"area":null},{"id":"2602.03979","title":"Likelihood-Based Reward Designs for General LLM Reasoning","created":"2026-02-03","cited_by_count":7,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2510.00931","title":"Making, not Taking, the Best of N","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2512.04558","title":"On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2505.20556","title":"Learning a Pessimistic Reward Model in RLHF","created":"2025-05-26","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2511.02833","title":"In Good GRACEs: Principled Teacher Selection for Knowledge Distillation","created":"2025-11-04","cited_by_count":5,"area":"distill"},{"id":"2604.16453","title":"Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo","created":"2026-04-07","cited_by_count":5,"area":null},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2505.13672","title":"A*-Decoding: Token-Efficient Inference Scaling","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2510.18982","title":"Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality","created":"2025-10-21","cited_by_count":4,"area":"lr"},{"id":"2512.19905","title":"Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling","created":"2025-12-22","cited_by_count":4,"area":"lr"},{"id":"2603.11331","title":"Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover","created":"2026-03-11","cited_by_count":4,"area":"alignment"},{"id":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2606.01667","title":"ATLAS: Agentic Test-time Learning-to-Allocate Scaling","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"id":"2506.15733","title":"$\\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts","created":"2025-06-15","cited_by_count":3,"area":"lr"},{"id":"2509.21091","title":"Best-of-$\\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.27355","title":"ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations","created":"2025-10-31","cited_by_count":3,"area":"lr"},{"id":"2603.06797","title":"Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment","created":"2026-03-06","cited_by_count":3,"area":"alignment"},{"id":"2604.04648","title":"From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2511.16324","title":"SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning","created":"2025-11-20","cited_by_count":2,"area":"alignment"},{"id":"2602.01485","title":"Predicting and improving test-time scaling laws via reward tail-guided search","created":"2026-02-01","cited_by_count":2,"area":"lr"},{"id":"2602.03787","title":"Inference-time Unlearning Using Conformal Prediction","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2602.16745","title":"PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2603.01335","title":"Provable and Practical In-Context Policy Optimization for Self-Improvement","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2605.14163","title":"Agentic Systems as Boosting Weak Reasoning Models","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2605.17609","title":"Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2606.03102","title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2602.09642","title":"MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering","created":"2026-02-10","cited_by_count":1,"area":"agents"},{"id":"2602.10217","title":"Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance","created":"2026-02-10","cited_by_count":1,"area":"safety"},{"id":"2602.21556","title":"Power and Limitations of Aggregation in Compound AI Systems","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2605.30619","title":"Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2605.31561","title":"What Am I Missing? Question-Answering as Hidden State Probing","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.05296","title":"Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2606.19354","title":"Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2606.28301","title":"VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing","created":"2026-06-26","cited_by_count":1,"area":"lr"},{"id":"2608.21496","title":"The geometry of AI validation: From structural blindness to reusable audits","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2609.35947","title":"FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models","created":"2026-09-28","cited_by_count":1,"area":"diffusion"},{"id":"2505.17288","title":"Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.16420","title":"Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2510.03520","title":"Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment","created":"2025-10-03","cited_by_count":0,"area":"alignment"},{"id":"2510.26219","title":"Test-time reward-guided alignment of language models by importance sampling on pre-logit space","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2602.07738","title":"Learnable Chernoff Baselines for Inference-Time Alignment","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.23535","title":"Partition Function Estimation under Bounded f-Divergence","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2604.04855","title":"The Role of Generator Access in Autoregressive Post-Training","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.16535","title":"SCATR: Simple Calibrated Test-Time Ranking","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2604.17207","title":"Demystifying the unreasonable effectiveness of online alignment methods","created":"2026-04-19","cited_by_count":0,"area":"alignment"},{"id":"2605.06219","title":"Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.13537","title":"Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.30131","title":"CCS: Clinical Consensus Selection for Radiology Report Generation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03217","title":"An Asymptotic Theory of Chain-of-Thought in In-Context Learning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.09635","title":"Gradient-Guided Reward Optimization for Inference-time Alignment","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2607.03453","title":"Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2608.08002","title":"Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees","created":"2026-08-08","cited_by_count":0,"area":"alignment"},{"id":"2608.11420","title":"Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.15402","title":"Towards a theory of inference-time alignment with unknown rewards","created":"2026-08-15","cited_by_count":0,"area":"alignment"},{"id":"2608.19748","title":"Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.24228","title":"Evaluating Multiple LLM Generations with Validated Task Coverage","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26324","title":"Privacy Without Regret: Differentially Private Inference-Time Alignment","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2608.29188","title":"Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2608.30051","title":"Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.08082","title":"Inference-Time Nash Alignment","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.14500","title":"When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.21899","title":"ExpBoN: Exponential-Noise Best-of-$n$ for Efficient Test-Time LLM Alignment","created":"2026-09-18","cited_by_count":0,"area":"alignment"},{"id":"2609.30352","title":"Strategic Self-Consistency","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.30456","title":"Spectral Feedback for Test-Time Alignment of Protein Diffusion Models","created":"2026-09-24","cited_by_count":0,"area":"diffusion"},{"id":"2609.33291","title":"The Statistical Benefits of Multiple Responses for Learning from Demonstrations","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.34639","title":"Uniform Race: Parameter-Free Approximate Rejection Sampling","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38104","title":"Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38526","title":"Revisiting scaling laws for reward optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.38672","title":"Provable Test-Time Scaling for Beam Search in LLM Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.08138","title":"Test-Time Agent Evolution for Long-Horizon Legal Reasoning","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08719","title":"Holdout Best-of-N: Unbiased Evaluation and Its Cost","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.12851","title":"Universal Bounds for Self-Normalized Kullback-Leibler Estimation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15372","title":"Fewer Bits, More Tries: Recovering Capability Under Memory Constraints","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19362","title":"Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems","created":"2026-10-14","cited_by_count":0,"area":"lr"},{"id":"2610.19890","title":"Frustratingly Easy Majority Voting Using Length Conditioning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}