Entity · benchmark
AIME
benchmarkactive
aime-00f528e9·5 events·first seen Aliases: AIME
Co-occurring entities
DeepSeek-R1-Distill-QwenToken Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought ModelsBIRDQwen3MATH-500Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning ProblemsQwen3-1.7BAdaPrefix-GRPOGRPO (Group Relative Policy Optimization)Neural Theorem ProverOpenAIIMOLeanAMC12o1-previewDeepSeek V4MATHDeepSeek-R1-Lite-Preview
More like this (12)
Recent events (5)
Linear probes on chain-of-thought hidden states can predict reasoning non-convergence early
A new arXiv preprint studies the bimodal convergence pattern in chain-of-thought models like DeepSeek-R1-Distill-Qwen-7B, where generations either complete within a token budget (90.3% accuracy on AIME) or exhaust it without concluding (6.6% accuracy), with a 62% overall convergence rate. The authors train linear probes on hidden-state activations at early token positions (50-300) and find that layer-20 activations at token 150 achieve AUC 0.608, reliably above chance and outperforming behavioral baselines from token entropy and repetition statistics. The results suggest convergence fate is partially encoded in intermediate representations early in generation, pointing toward early-exit inference and adaptive compute allocation strategies. Statistical evidence is modest (permutation test p=0.063), limiting strong conclusions.
BIRD: Bootstrapped Iterative Self-Reasoning Distillation reduces LLM chain-of-thought length while improving accuracy
Researchers introduce BIRD (Bootstrapped Iterative Self-Reasoning Distillation), a two-stage method for compressing chain-of-thought reasoning in large language models without sacrificing accuracy. The approach first fine-tunes a model on brevity-instructed correct traces to warm-start the rollout distribution, then applies on-policy reverse-KL distillation against a concise self-teacher. On Qwen3-8B, BIRD improves MATH-500 accuracy from 86.2% to 92.0% while cutting average response length from 3,099 to 1,115 tokens, outperforming cold-start on-policy distillation baselines.
AdaPrefix-GRPO: Adaptive prefix control doubles GRPO accuracy on hard math reasoning
A new arXiv preprint introduces AdaPrefix-GRPO, a method that addresses GRPO's failure to learn from problems where no rollout succeeds by prepending correct solution prefixes and dynamically adjusting prefix length to maintain ~50% success rate per problem throughout training. The prefix assistance is gradually withdrawn so the final model solves problems unaided. On hard math benchmarks, the method more than doubles GRPO accuracy for a 0.6B model (2.1x) and achieves 1.7x improvement on AIME, while halving trace length, with larger gains on smaller models. The implementation requires only data preparation changes and a loss mask, leaving the trainer unchanged.
OpenAI Neural Theorem Prover Solves Formal Math Olympiad Problems in Lean
OpenAI developed a neural theorem prover integrated with the Lean proof assistant that can solve challenging high-school olympiad problems, including problems from AMC12, AIME, and two IMO-adapted problems. The system demonstrates automated formal mathematical reasoning at a level previously requiring human expertise. This represents a significant capability milestone in AI-assisted formal verification and mathematical problem-solving.
DeepSeek-R1-Lite-Preview Launched with o1-Level Reasoning Performance
DeepSeek has released DeepSeek-R1-Lite-Preview, a reasoning-focused model claiming o1-preview-level performance on AIME and MATH benchmarks. The model features a transparent, real-time chain-of-thought process and demonstrates inference scaling behavior where longer reasoning chains yield better results. DeepSeek has indicated that open-source model weights and a full API are forthcoming. The model is currently accessible via chat.deepseek.com.