메뉴
Solve IMO-level problems through multi-stage hierarchical reasoning with lemma-based memory compression. Intern-S1-MO achieves 26/35 on IMO2025 geometry-excluded problems—ideal when complex reasoning exceeds single-pass context.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/ADu2021/skillXiv --skill olympiad-long-horizon-reasoning명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers produce different types of usable knowledge. A single paper can yield multiple skills if it spans categories. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.
Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose model-based augmentation to reduce error dependence from H² to H.
Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining fidelity and text-alignment.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | olympiad-long-horizon-reasoning |
| title | Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving |
| version | 0.0.2 |
| engine | skillxiv-v0.0.2-claude-opus-4.6 |
| license | MIT |
| url | https://arxiv.org/abs/2512.10739 |
| keywords | ["mathematical reasoning","multi-agent systems","reinforcement learning","olympiad problems","hierarchical decomposition"] |
| description | Solve IMO-level problems through multi-stage hierarchical reasoning with lemma-based memory compression. Intern-S1-MO achieves 26/35 on IMO2025 geometry-excluded problems—ideal when complex reasoning exceeds single-pass context. |
The system overcomes context-length limitations through multi-round hierarchical reasoning where intermediate insights are stored as lemmas. A verification agent validates solutions while RL continuously improves the underlying reasoning model.
Hierarchical reasoning with lemma-based compression:
# Multi-agent Olympiad reasoning system
class OlympiadReasoner:
def __init__(self):
self.reasoner = ReasoningModel()
self.verifier = VerificationModel()
self.lemma_store = LemmaMemory()
def solve_problem_hierarchically(self, problem, max_rounds=10):
"""Multi-round reasoning with lemma compression."""
context = problem
solution_steps = []
for round_idx in range(max_rounds):
# Stage 1: Reasoning on current context
reasoning = self.reasoner.generate_reasoning(context)
# Check if solution found
if self.is_complete_solution(reasoning):
return reasoning
# Stage 2: Extract lemmas (compress intermediate insights)
lemmas = self.extract_lemmas(reasoning)
self.lemma_store.add_lemmas(lemmas)
context = .compress_context(
context,
lemmas,
max_tokens=
)
solution_steps.append(reasoning)
.join(solution_steps)
():
lemmas = []
lemma_candidates = .find_mathematical_facts(reasoning_text)
candidate lemma_candidates:
importance = .score_lemma_importance(
candidate,
reasoning_text
)
importance > :
lemmas.append({
: candidate,
: importance,
: (.lemma_store)
})
lemmas
():
verification_report = .verifier.verify(solution)
verification_report[]:
errors = verification_report[]
errors