AIBullisharXiv – CS AI · Jun 57/10
🧠Researchers introduce Dynamic Thinking-Token Selection (DynTS), a method that optimizes Large Reasoning Models by identifying and retaining only decision-critical tokens during inference while discarding redundant reasoning trace data. This approach significantly reduces memory footprint and computational overhead, addressing a major efficiency bottleneck in LRMs that generate extended reasoning sequences.
AIBearisharXiv – CS AI · Jun 37/10
🧠Researchers demonstrate that Large Reasoning Models (LRMs) frequently 'overthink' problems after reaching correct answers, with continued reasoning degrading accuracy by up to 21%. The study introduces a protocol to measure reasoning sufficiency and reveals that harmful overthinking—where additional reasoning destabilizes correct solutions—represents a broader reliability risk affecting both multimodal and language-only models.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers introduce RT-LRM, a comprehensive benchmark for evaluating the trustworthiness of Large Reasoning Models across truthfulness, safety, and efficiency dimensions. The study reveals that LRMs face significant vulnerabilities including CoT-hijacking and prompt-induced inefficiencies, demonstrating they are more fragile than traditional LLMs when exposed to reasoning-induced risks.
AIBullisharXiv – CS AI · Apr 67/10
🧠Researchers discovered that in Large Reasoning Models like DeepSeek-R1, the first solution is often the best, with alternative solutions being detrimental due to error accumulation. They propose RED, a new framework that achieves up to 19% performance gains while reducing token consumption by 37.7-70.4%.
AIBullisharXiv – CS AI · Mar 37/102
🧠Researchers propose Intervened Preference Optimization (IPO) to address safety issues in Large Reasoning Models, where chain-of-thought reasoning contains harmful content even when final responses appear safe. The method achieves over 30% reduction in harmfulness while maintaining reasoning performance.
AIBullisharXiv – CS AI · Mar 37/104
🧠Researchers introduced AgentMath, a new AI framework that combines language models with code interpreters to solve complex mathematical problems more efficiently than current Large Reasoning Models. The system achieves state-of-the-art performance on mathematical competition benchmarks, with AgentMath-30B-A3B reaching 90.6% accuracy on AIME24 while remaining competitive with much larger models like OpenAI-o3.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers propose treating AI behavior forecasting as a learnable task rather than relying on explainability methods, training specialized models to predict how large reasoning models will perform on new inputs. Behavior Forecasters outperform GPT-5.4 and Claude Opus-4.6 at predicting LRM consistency and input-sensitivity while operating at significantly lower inference costs.
🧠 GPT-5🧠 Claude
AIBullisharXiv – CS AI · Jun 86/10
🧠Researchers introduce DyCon, a training-free framework that dynamically models task difficulty during reasoning to reduce inefficiencies in Large Reasoning Models. The method leverages step-level embeddings to control reasoning depth, achieving significant efficiency gains across multiple model sizes and benchmarks without sacrificing accuracy.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduced LocalSearchBench, a comprehensive benchmark for testing AI agents in local life services, revealing significant performance gaps even among state-of-the-art large reasoning models. The benchmark comprises 1.3M merchant entries and 900 multi-hop reasoning tasks, exposing critical weaknesses in completeness and faithfulness that underscore the need for domain-specific AI agent development.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers compared frontier Large Reasoning Models (LRMs) with traditional AI systems using human gameplay data paired with fMRI brain recordings. LRMs demonstrated superior alignment with human learning behavior and predicted brain activity an order of magnitude better than reinforcement learning alternatives, suggesting they more closely mirror human cognition during complex decision-making.
AINeutralarXiv – CS AI · May 76/10
🧠Researchers introduce ReasoningGuard, an inference-time safety mechanism designed to protect Large Reasoning Models from generating harmful content during their reasoning processes. The method uses internal attention mechanisms to inject safety-oriented reflections at critical points, mitigating jailbreak attacks without requiring costly fine-tuning and outperforming nine existing safeguards.
AINeutralarXiv – CS AI · Apr 76/10
🧠Researchers propose a new framework for 'selective forgetting' in Large Reasoning Models (LRMs) that can remove sensitive information from AI training data while preserving general reasoning capabilities. The method uses retrieval-augmented generation to identify and replace problematic reasoning segments with benign placeholders, addressing privacy and copyright concerns in AI systems.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers developed monitoring strategies to detect when Large Reasoning Models are engaging in unproductive reasoning by identifying early failure signals. The new techniques reduce token usage by 62.7-93.6% while maintaining accuracy, significantly improving AI model efficiency.
AIBearisharXiv – CS AI · Mar 36/104
🧠Researchers introduced HardcoreLogic, a benchmark of over 5,000 logic puzzles across 10 games to test Large Reasoning Models (LRMs) on non-standard puzzle variants. The study reveals significant performance drops in current LRMs when faced with complex or uncommon puzzle variations, indicating heavy reliance on memorized patterns rather than genuine logical reasoning.
AIBullisharXiv – CS AI · Feb 276/106
🧠Researchers introduce SideQuest, a novel KV cache management system that uses Large Reasoning Models to compress memory usage during long-horizon AI tasks. The system reduces peak token usage by up to 65% while maintaining accuracy by having the model itself determine which tokens are useful to keep in memory.
AIBullisharXiv – CS AI · Feb 276/106
🧠Researchers developed a two-stage framework to optimize large reasoning models, reducing overthinking on simple queries while maintaining accuracy on complex problems. The approach achieved up to 3.7 accuracy point improvements while reducing token generation by over 40% through hybrid fine-tuning and adaptive reinforcement learning techniques.
