StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

arXiv:2609.00787 · cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.AI

Submitted: 2026-09-01

Updated: 2026-09-07

Code: https://github.com/thunlp/StudyBench

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Verifier — 21× in this paper · explained in 2 episodes
• Accuracy — 18× in this paper · explained in 1 episode
• Trace — 17× in this paper · explained in 2 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• Adaptation — 11× in this paper · explained in 1 episode
• Consistency — 8× in this paper · explained in 3 episodes
• Benchmarking — 6× in this paper · explained in 4 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Quantum Physics — 4× in this paper · explained in 11 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Analyzer — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Conservation Laws — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization
• A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
• The Llama 3 Herd of Models
• R-Zero: Self-Evolving Reasoning LLM from Zero Data
• MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
• SPICE: Self-Play In Corpus Environments Improves Reasoning
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• Humanity's Last Exam
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
• Qwen3 Technical Report
• SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
• Self-Rewarding Language Models
• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection