AIME 2025
aime-2025-fa536129·3 events·first seen 1mo agoAliases: AIME 2025
Co-occurring entities
More like this (12)
Recent events (3)
RA-RFT: Retrieval-Augmented Reinforcement Fine-Tuning teaches LLMs to reason by analogy
Researchers propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that trains a retriever to rank contexts by expected reasoning benefit rather than semantic similarity, then fine-tunes a policy model via reinforcement learning using retrieved analogous demonstrations. The key insight is that reasoning-relevant retrieval surfaces complementary solution strategies rather than superficially similar problems. On mathematical reasoning benchmarks, RA-RFT improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively, suggesting reasoning-aware retrieval is orthogonal to reward design and training curriculum improvements.
Mistral Releases Mistral 3 Family: Mistral Large 3 (675B MoE) and Ministral 3 Series (3B–14B), All Apache 2.0
Mistral AI has announced Mistral 3, a family of open-weight models including Mistral Large 3 (41B active / 675B total sparse MoE) and three dense Ministral 3 edge models (3B, 8B, 14B), all released under Apache 2.0. Mistral Large 3 debuts at #2 on LMArena's OSS non-reasoning leaderboard, supports image understanding, and was trained on 3,000 NVIDIA H200 GPUs; a reasoning variant is forthcoming. The Ministral 3 series includes base, instruct, and reasoning variants with multimodal and multilingual capabilities, with the 14B reasoning model achieving 85% on AIME '25. The release involves deep co-optimization with NVIDIA (Blackwell/Hopper kernels, NVFP4 format), vLLM, and Red Hat, and is available across major cloud and inference platforms.
Pair-In, Pair-Out (PIPO): Unified Latent Compression and Multi-Token Prediction for Efficient LLM Inference
PIPO is a new inference efficiency framework that unifies input-side latent compression with output-side multi-token prediction (MTP) by treating them as mirror operations: a compressor folds two input tokens into one latent, while an MTP head unfolds one hidden state into an additional output token. To avoid the expensive verifier pass typically required by speculative decoding, PIPO trains a lightweight confidence head using On-Policy Distillation (OPD), which naturally aligns with rejection-sampling criteria. Experiments on Qwen3.5-4B and 9B backbones across AIME 2025, GPQA-Diamond, LiveCodeBench v6, and LongBench v2 show up to 2.64× first-token-latency speedup and +7.15 pass@4 improvement over regular decoding.