AxDafny achieves 92.7% verification success on DafnyBench (6.5 points above prior proof-hint baselines) via verifier-guided repair and introduces the LCB-Pro-Dafny benchmark of 250 problems.
Livecodebench pro: How do olympiad medalists judge llms in competitive programming?arXiv preprint arXiv:2506.11928
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 9roles
dataset 1polarities
use dataset 1representative citing papers
CodeSpecBench shows LLMs achieve at most 20.2% pass rate on repository-level executable behavioral specification generation, revealing that strong code generation does not imply deep semantic understanding.
TESSY creates stylistically consistent synthetic data via teacher-student token interleaving, yielding 11.25% and 6.68% gains on code benchmarks where pure teacher data causes 3.25% and 10.02% drops.
Fine-tuning LLMs on a novel, syntax-friendly but feature-poor language teaches parsing without closing the gap between PyLang and Python pass rates.
OpenDeepThink uses Bradley-Terry aggregation of LLM pairwise judgments to rank and evolve parallel reasoning traces, improving Gemini 3.1 Pro Codeforces Elo by 405 points over eight rounds.
On Codeforces problems, independent k-shot sampling achieves better accuracy-cost and accuracy-query tradeoffs than agentic reasoning, even with prompt caching.
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
Multi-LCB extends LiveCodeBench to 12 languages by translating Python tasks, revealing Python overfitting and performance disparities when evaluating 24 LLMs.
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.
citing papers explorer
-
AxDafny: Agentic Verified Code Generation in Dafny
AxDafny achieves 92.7% verification success on DafnyBench (6.5 points above prior proof-hint baselines) via verifier-guided repair and introduces the LCB-Pro-Dafny benchmark of 250 problems.
-
CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
CodeSpecBench shows LLMs achieve at most 20.2% pass rate on repository-level executable behavioral specification generation, revealing that strong code generation does not imply deep semantic understanding.
-
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
TESSY creates stylistically consistent synthetic data via teacher-student token interleaving, yielding 11.25% and 6.68% gains on code benchmarks where pure teacher data causes 3.25% and 10.02% drops.
-
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
Fine-tuning LLMs on a novel, syntax-friendly but feature-poor language teaches parsing without closing the gap between PyLang and Python pass rates.
-
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
OpenDeepThink uses Bradley-Terry aggregation of LLM pairwise judgments to rank and evolve parallel reasoning traces, improving Gemini 3.1 Pro Codeforces Elo by 405 points over eight rounds.
-
When Independent Sampling Outperforms Agentic Reasoning
On Codeforces problems, independent k-shot sampling achieves better accuracy-cost and accuracy-query tradeoffs than agentic reasoning, even with prompt caching.
-
Seed1.8 Model Card: Towards Generalized Real-World Agency
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
-
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
Multi-LCB extends LiveCodeBench to 12 languages by translating Python tasks, revealing Python overfitting and performance disparities when evaluating 24 LLMs.
-
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.