Researchers propose TTSR, a test-time training framework where a single LLM alternates between Student and Teacher roles to improve its own reasoning. The method generates targeted variant questions based on analyzed failure patterns, showing consistent improvements across mathematical reasoning benchmarks without relying on unreliable pseudo-labels.
A new research paper proposes Rewards as Labels (REAL), a framework that reframes reinforcement learning with verifiable rewards as a classification problem rather than scalar weighting. The method addresses fundamental gradient optimization issues in current GRPO variants and demonstrates measurable improvements on mathematical reasoning benchmarks.
Researchers introduce NeuroProlog, a neurosymbolic framework that compiles math word problems into executable Prolog programs with formal verification guarantees. A multi-task "Cocktail" training strategy achieves significant accuracy improvements on GSM8K: +5.23% on Qwen-32B, +3.43% on GPT-OSS-20B, and +5.54% on Llama-3B compared to single-task baselines.
Researchers propose LaDiR, a framework that replaces traditional autoregressive decoding with latent diffusion models to improve LLM reasoning. The approach encodes reasoning steps into compressed latent representations and uses bidirectional attention to refine solutions iteratively, enabling parallel exploration of diverse reasoning paths.
Researchers have identified a critical gap in how large language models learn mathematics: they can solve problems but often don't understand the underlying concepts. A new reinforcement learning framework called CORE addresses this by using explicit concept definitions as training signals, rather than just reinforcing correct final answers.
Researchers propose LaDiR (Latent Diffusion Reasoner), a framework that combines variational autoencoders and latent diffusion models to improve LLM reasoning. The approach encodes reasoning steps into continuous latent representations, enabling iterative refinement and parallel generation of diverse solutions beyond traditional autoregressive decoding.