Records found: 8
'Agent0 co-evolves a curriculum agent and an executor from the same base LLM, using sandboxed Python tool calls and ambiguity-aware RL to improve math and general reasoning without external data.'
ByteDance introduces Seed-Prover, a novel lemma-centric system that achieves breakthrough results in automated mathematical theorem proving, solving 5 out of 6 IMO 2025 problems and excelling across multiple benchmarks.
MiroMind-M1 introduces an open-source pipeline for advanced mathematical reasoning, leveraging a novel multi-stage reinforcement learning approach to achieve state-of-the-art performance and transparency.
Microsoft introduces Phi-4-mini-Flash-Reasoning, a compact 3.8B parameter model optimized for efficient long-context reasoning and fast inference, outperforming previous models on complex benchmarks.
Meta and NYU developed a semi-online reinforcement learning method that balances offline and online training to enhance large language model alignment, boosting performance in both instruction-based and mathematical tasks.
OMEGA is a novel benchmark designed to probe the reasoning limits of large language models in mathematics, focusing on exploratory, compositional, and transformational generalization.
Researchers reveal that training large language models with just one example using 1-shot reinforcement learning significantly enhances their math reasoning abilities, matching results from large datasets.
Xiaomi's MiMo-7B is a compact language model that surpasses larger models in math and code reasoning through advanced pre-training and reinforcement learning strategies.