AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers introduce Proactive Interactive Reasoning (PIR), a new paradigm that enables large language models to ask clarifying questions during problem-solving rather than operating blindly with incomplete information. The approach combines supervised fine-tuning and policy optimization to achieve significant improvements in mathematical reasoning, code generation, and document editing tasks while reducing computational overhead.
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers propose PEAR, a novel supervised fine-tuning (SFT) method that optimizes language models with downstream reinforcement learning in mind rather than in isolation. The approach uses importance sampling to reweight training data, addressing a critical distribution mismatch between offline SFT and online RL stages, achieving up to 14.6% performance gains on mathematical reasoning benchmarks.
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers introduce PuzzleClone, a DSL-driven framework that automatically synthesizes large-scale, verifiable datasets for training LLMs on mathematical and logical reasoning tasks. The team generates PC-83K, a benchmark of 83,000+ diverse puzzles, and demonstrates that models fine-tuned on this dataset achieve substantial performance improvements across multiple logic and mathematical benchmarks.
AINeutralarXiv – CS AI · 2d ago7/10
🧠FormInv introduces a measurement protocol that audits mathematical reasoning benchmarks for semantic consistency, revealing that current evaluation methods mask significant ranking volatility across AI models. The study found 3.1% semantically incorrect paraphrases in MathCheck that altered model rankings and discovered that models achieving similar accuracy scores (86-96%) exhibit drastically different consistency rates (50-82%) when tested against semantically equivalent problem restatements.
🧠 GPT-4🧠 Claude🧠 Haiku
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers propose DenseSteer, a training-free framework that improves mathematical reasoning in small language models (≤3B parameters) by steering internal representations toward denser reasoning patterns. The method demonstrates that smaller models can match larger ones' performance by executing fewer, more information-rich reasoning steps rather than verbose chain-of-thought processes.
AIBullisharXiv – CS AI · 2d ago7/10
🧠DeepTool is a new AI framework that enhances large language models' ability to reason through tool use by implementing process-supervised reinforcement learning. The system dramatically improves performance on mathematical benchmarks like AIME24 (3.2% to 40.4%) while maintaining token efficiency through interleaved thinking and action.
AIBullisharXiv – CS AI · 4d ago7/10
🧠Researchers propose STARS, a training framework that stabilizes Looped Language Models (LoopLMs) to enable reliable test-time scaling through latent reasoning. The method uses Jacobian Spectral Radius Regularization to constrain neural states toward stable fixed points, addressing a critical problem where model performance peaks then collapses with increased recurrence depth.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers propose Theorem-SFT, a novel supervised fine-tuning approach that teaches language models to apply mathematical rules explicitly rather than memorize surface-level correlations between problems and solutions. The method demonstrates significant performance improvements across benchmarks while revealing that feed-forward layers, not memorization itself, are the primary locus of reasoning capability.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers propose CIKA, a framework using LLMs as interventional simulators to identify which mathematical concepts causally contribute to correct answers, distinguishing genuine causal relationships from spurious correlations. The method achieves 69.7% on Omni-MATH-Rule and 97.2% on GSM8K with a frozen 7B model, outperforming o1-mini on contamination-free benchmarks.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers introduce Distribution Guided Policy Optimization (DGPO), a novel reinforcement learning framework that improves how large language models learn to perform complex reasoning tasks by assigning credit at the token level rather than sequence level. DGPO replaces unstable KL divergence penalties with bounded Hellinger distance and adds an entropy gating mechanism, achieving state-of-the-art performance on challenging math benchmarks like AIME2024 and AIME2025.
AINeutralarXiv – CS AI · May 117/10
🧠Researchers introduce GSM-SEM, a framework for generating semantically diverse variants of math benchmarks like GSM8K to combat memorization in LLM evaluations. Testing 14 state-of-the-art models reveals consistent performance drops averaging 28%, suggesting current leaderboard rankings may overstate true reasoning capabilities.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers propose ESSAM, a novel training framework combining Evolution Strategies with Sharpness-Aware Maximization to fine-tune large language models for mathematical reasoning while dramatically reducing GPU memory requirements. The approach achieves comparable accuracy to reinforcement learning methods like PPO and GRPO while using 18-10× less memory, addressing a critical bottleneck in LLM development.
AIBullisharXiv – CS AI · May 97/10
🧠Researchers introduce Asymmetric Group Policy Optimization (AGPO), a reinforcement learning method that improves LLM reasoning by preventing capability collapse while focusing on rare correct solutions. The technique demonstrates state-of-the-art performance on mathematical benchmarks and has been deployed in JD's search ads relevance system, showing practical industrial applications.
AINeutralarXiv – CS AI · Apr 207/10
🧠Researchers conducted a comprehensive empirical study on scaling laws for large language models during reinforcement learning post-training, using Qwen2.5 models ranging from 0.5B to 72B parameters. The study reveals that larger models demonstrate superior learning efficiency, performance can be predicted via power-law models, and data reuse proves highly effective in constrained environments, providing practical guidelines for optimizing LLM reasoning capabilities.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce Lightning OPD, an offline on-policy distillation framework that eliminates the need for live teacher inference servers during large language model post-training. By enforcing 'teacher consistency'—using the same teacher model for both supervised fine-tuning and distillation—the method achieves comparable performance to standard OPD while delivering 4x speedup and significantly reducing infrastructure costs.
AIBearisharXiv – CS AI · Apr 137/10
🧠Researchers have developed a 14-technique perturbation pipeline to test the robustness of large language models' reasoning capabilities on mathematical problems. Testing reveals that while frontier models maintain resilience, open-weight models experience catastrophic accuracy collapses up to 55%, and all tested models degrade when solving sequential problems in a single context window, suggesting fundamental architectural limitations in current reasoning systems.
🧠 Claude🧠 Opus
AIBullisharXiv – CS AI · Apr 137/10
🧠Researchers propose Distributionally Robust Token Optimization (DRTO), a method combining reinforcement learning from human feedback with robust optimization to improve large language model consistency across distribution shifts. The approach demonstrates 9.17% improvement on GSM8K and 2.49% on MathQA benchmarks, addressing LLM vulnerabilities to minor input variations.
AIBullisharXiv – CS AI · Apr 107/10
🧠Researchers propose the Master Key Hypothesis, suggesting that AI model capabilities can be transferred across different model scales without retraining through linear subspace alignment. The UNLOCK framework demonstrates training-free capability transfer, achieving significant accuracy improvements such as 12.1% gains on mathematical reasoning tasks when transferring from larger to smaller models.
AIBearisharXiv – CS AI · Apr 107/10
🧠Researchers introduced Riemann-Bench, a private benchmark of 25 expert-curated mathematics problems designed to evaluate AI systems on research-level reasoning beyond competition mathematics. The benchmark reveals that all frontier AI models currently score below 10%, exposing a significant gap between olympiad-level problem solving and genuine mathematical research capabilities.
AIBullisharXiv – CS AI · Apr 77/10
🧠Researchers developed QED-Nano, a 4B parameter AI model that achieves competitive performance on Olympiad-level mathematical proofs despite being much smaller than proprietary systems. The model uses a three-stage training approach including supervised fine-tuning, reinforcement learning, and reasoning cache expansion to match larger models at a fraction of the inference cost.
🧠 Gemini
AIBullisharXiv – CS AI · Mar 267/10
🧠Researchers introduce Hybrid Distillation Policy Optimization (HDPO), a new method that improves large language model training for mathematical reasoning by addressing 'cliff prompts' where standard reinforcement learning fails. The technique uses privileged self-distillation to provide learning signals for previously unsolvable problems, showing measurable improvements in coverage metrics while maintaining accuracy.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers released Phi-4-reasoning-vision-15B, a compact open-weight multimodal AI model that combines vision and language capabilities with strong performance in scientific and mathematical reasoning. The model demonstrates that careful architecture design and high-quality data curation can enable smaller models to achieve competitive performance with less computational resources.
AIBearisharXiv – CS AI · Mar 57/10
🧠Research reveals that state-of-the-art AI mathematical reasoning models like Qwen2.5-Math-7B achieve 61% accuracy primarily through unreliable computational pathways, with only 18.4% using stable reasoning. The study exposes that 81.6% of correct predictions come from inconsistent methods and 8.8% are confident but incorrect outputs.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers introduce MASS, a meta-learning framework that enables large language models to self-adapt at test time by generating synthetic training data and performing targeted self-updates. The system uses bilevel optimization to meta-learn data-attribution signals and optimize synthetic data through scalable meta-gradients, showing effectiveness in mathematical reasoning tasks.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers introduce TTSR, a new framework that enables AI models to improve their reasoning abilities during test time by having a single model alternate between student and teacher roles. The system allows models to learn from their mistakes by analyzing failed reasoning attempts and generating targeted practice questions for continuous improvement.
