{"total":62,"rows":[{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2606.24597","title":"Qwen-AgentWorld: Language World Models for General Agents","created":"2026-06-23","cited_by_count":28,"area":"wm"},{"id":"2606.23038","title":"EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning","created":"2026-06-22","cited_by_count":14,"area":"alignment"},{"id":"2605.03871","title":"EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics","created":"2026-05-05","cited_by_count":13,"area":"alignment"},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2603.23522","title":"Qworld: Question-Specific Evaluation Criteria for LLMs","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2605.25240","title":"JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2605.06822","title":"SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.26579","title":"Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards","created":"2026-05-26","cited_by_count":4,"area":"alignment"},{"id":"2605.30803","title":"PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2606.17029","title":"DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents","created":"2026-06-15","cited_by_count":4,"area":"lr"},{"id":"2604.01375","title":"The Hitchhikers Guide to Rubric Quality Understanding and Enrichment","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2604.13618","title":"C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.26046","title":"When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2607.01830","title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","created":"2026-07-02","cited_by_count":3,"area":"alignment"},{"id":"2608.02831","title":"Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning","created":"2026-08-03","cited_by_count":3,"area":null},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2604.26020","title":"Training Computer Use Agents to Assess the Usability of Graphical User Interfaces","created":"2026-04-28","cited_by_count":2,"area":"agents"},{"id":"2605.13486","title":"R^2-Mem: Reflective Experience for Memory Search","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.15092","title":"Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2608.03527","title":"Training Documents Reranker with Search Rubrics for Deep Research Agent","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2609.36893","title":"Momentum-Coupled Rubric Adaptation for Detailed Image Captioning","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2604.28181","title":"Synthetic Computers at Scale for Long-Horizon Productivity Simulation","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.29275","title":"Prompt-Level Reward Specifications for Open-Ended Post-Training","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2606.08077","title":"Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics","created":"2026-06-06","cited_by_count":1,"area":"synth"},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.04077","title":"FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.12097","title":"Graph-Structured Rubrics: Compiling Rubrics into Typed Evaluation Graphs for LLM Judges","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.01572","title":"From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.12459","title":"EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning","created":"2026-09-11","cited_by_count":1,"area":"lr"},{"id":"2610.05308","title":"RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation","created":"2026-10-04","cited_by_count":1,"area":"alignment"},{"id":"2605.01630","title":"Prosa: Rubric-Based Evaluation of LLMs on Real User Chats in Brazilian Portuguese","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"},{"id":"2605.23384","title":"Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2605.28882","title":"GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human","created":"2026-05-26","cited_by_count":0,"area":"synth"},{"id":"2605.30947","title":"Extending AI for Research to the Humanities: A Multi-Agent Framework for Evidence-Grounded Scholarship","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.00609","title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2607.02374","title":"DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.19824","title":"Rewarding Better Thinking for LLM Preference Alignment","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2607.20862","title":"CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.29559","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.01810","title":"RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.14212","title":"APTER: Adaptive Post-Training with Expert-Grounded Rubrics","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.18744","title":"Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.31076","title":"Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.30604","title":"The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.34296","title":"Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36652","title":"RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.37145","title":"From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38792","title":"Training LLM Judges from Language Feedback via Position-Selective Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2609.38847","title":"Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.02824","title":"MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.04087","title":"DUET: Co-Evolving Solver and Grader Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.08781","title":"IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10809","title":"Evaluating Rubric Generation with Interventional Transfer","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11281","title":"How to post-train on a surrogate: Envelope sampling mitigates reward hacking","created":"2026-10-08","cited_by_count":0,"area":"alignment"},{"id":"2610.13375","title":"From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17609","title":"Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19915","title":"Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}