Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

arXiv:2602.03619 · cs.CL · Submitted 2026-02-03 · Read on arXiv

cs.CL

Submitted: 2026-02-03

Updated: 2026-09-02

Code: https://github.com/THUDM/slime

Terminology

• GRPO — 28× in this paper · explained in 6 episodes
• Consistency — 15× in this paper · explained in 3 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 11× in this paper · explained in 3 episodes
• Alignment — 10× in this paper · explained in 1 episode
• Large Language Model — 10× in this paper
• Core — 9× in this paper · explained in 2 episodes
• AUC — 6× in this paper · explained in 2 episodes
• Evaluation Dimensions — 6× in this paper · explained in 3 episodes
• Aggregation — 5× in this paper · explained in 1 episode
• Calibration — 4× in this paper · explained in 7 episodes
• Pairwise Comparisons — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Redundancy — 3× in this paper · explained in 2 episodes
• Verifiable Rewards — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Context Parallel — 2× in this paper
• Expert Parallel — 2× in this paper
• Supervised Fine-Tuning — 2× in this paper
• Tensor Parallel — 2× in this paper
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Overview of Multi-Agent Markov-State — 1× in this paper
• RAG — 1× in this paper · explained in 3 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• CL-bench: A Benchmark for Context Learning
• DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• GPT-4 Technical Report
• Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
• IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
• Reinforcement Learning with Rubric Anchors
• CL-bench Life: Can Language Models Learn from Real-Life Context?
• Humanity's Last Exam
• DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports
• HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability
• AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
• WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
• GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
• DeepSeek-V3 Technical Report
• P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
• DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering