AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers propose a joint optimization framework for deploying large language model reasoning on resource-constrained edge devices, combining adaptive chain-of-thought prompting with distributed mixture-of-experts architecture. The framework dynamically balances reasoning quality and computational efficiency by treating reasoning depth as an optimizable network resource, achieving 90% accuracy and latency satisfaction with minimal inference overhead.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce Stepwise Confidence Attribution (SCA), a framework for diagnosing where large language models fail in multi-step reasoning tasks without requiring access to the model's internal parameters. The method identifies problematic reasoning steps by measuring confidence alignment with consensus patterns across correct solutions, improving self-correction accuracy by up to 13.5%.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers propose AGCLR, a new method that enhances large language models' reasoning capabilities by introducing persistent memory across reasoning steps. The approach addresses a fundamental limitation in continuous latent reasoning where intermediate facts are lost as models explore deeper reasoning paths, demonstrating consistent improvements on mathematical and multi-hop reasoning benchmarks.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers introduce ISPO (Intrinsic Signal Policy Optimization), a new reinforcement learning method that improves long-chain reasoning in large language models by densifying reward signals with intrinsic metrics derived from the model's own probabilities. The approach addresses critical failure modes in existing GRPO-based methods and shows consistent improvements across mathematical reasoning benchmarks.
AINeutralarXiv – CS AI · Jun 96/10
🧠AeroSpectra Sentinel is a research prototype that combines STFT audio analysis, machine learning, and LLM prompt-chaining to assist in acute asthma risk assessment from respiratory sounds and clinical signals. Evaluated on respiratory sound datasets, the system achieved up to 91.10% binary accuracy with random forest models, while structured prompting with guardrails and FHIR validation showed strongest safety consistency in simulated clinical scenarios.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers demonstrate that simple K-nearest neighbor models leveraging biological knowledge graphs achieve competitive performance in predicting gene knockout effects on transcriptomic expression, with reinforcement learning-optimized LLMs further improving results to match state-of-the-art methods. This work suggests knowledge graphs serve as effective model priors for complex biological prediction tasks.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers introduce CLPO, a curriculum learning framework that dynamically adapts training difficulty for large language models during reinforcement learning. The approach automatically identifies solved, medium, and hard problems, then strategically restructures tasks to match the model's evolving capabilities, achieving substantial improvements over existing methods on mathematical and reasoning benchmarks.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduced MatSciBench, a comprehensive benchmark of 1,340 college-level materials science problems designed to evaluate large language models' reasoning abilities in this specialized domain. Testing leading LLMs revealed significant limitations, with DeepSeek-R1 achieving 75.22% accuracy on text questions and GPT-4 reaching 53.02% on multimodal tasks, highlighting gaps in domain knowledge, calculation accuracy, and scientific figure interpretation.
🧠 GPT-5
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers propose EP-HUBO, a quantum-inspired optimization method that improves how large language models aggregate reasoning chains for evidence-intensive tasks like legal reasoning. By treating evidence selection as a combinatorial optimization problem rather than using simple majority voting, the approach preserves accurate minority hypotheses and achieves better performance on legal benchmarks.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers demonstrate that vector-based retrieval systems fail on queries requiring structural reasoning over knowledge graphs, proposing instead an LLM Query Planner with typed traversal primitives that outperforms traditional approaches. The study reveals that LLM capability gaps in graph reasoning stem not from model intelligence but from insufficient computational operators, with implications for enterprise knowledge systems.
AINeutralarXiv – CS AI · Jun 56/10
🧠ReasoningFlow is a framework that maps the complex, non-linear reasoning traces of large reasoning models into directed acyclic graphs, enabling better understanding and monitoring of AI reasoning processes. Through analysis of 1,260 traces across multiple models and tasks, researchers discovered that LRMs exhibit structurally similar reasoning patterns despite different training origins, while most erroneous steps don't influence final answers.
AIBullisharXiv – CS AI · Jun 56/10
🧠Researchers propose InfoDensity, a reinforcement learning reward framework that optimizes Large Language Models for efficient reasoning by measuring information density rather than just output length. The method tracks entropy trajectories to identify high-quality intermediate reasoning steps, achieving better accuracy-efficiency trade-offs on mathematical and general reasoning benchmarks.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers propose a framework for multi-agent systems that treats disagreement as valuable information rather than error to be eliminated. The approach abstracts reasoning traces into four symbolic disagreement states and applies strategic routing rules to content moderation and AI collaboration tasks.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce MechSim, a neuro-symbolic framework that enables large language models to reason transparently about the assumptions and mechanisms underlying scientific simulators. The approach improves explainability and decision-making reliability in high-stakes simulation-driven applications by treating simulators as structured systems rather than black boxes.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce Deontic Agentic Reasoning (DAR), a new framework that enables large language models to better tackle complex rule-based reasoning tasks by dynamically querying statutes and policies. Testing on DeonticBench shows agentic approaches improve performance on hard cases, though weaker models struggle with numerical reasoning and consume significantly more tokens.
AINeutralarXiv – CS AI · Jun 36/10
🧠Researchers demonstrate that visual graph structures serve as more effective reasoning scaffolds for large language models than text-based representations, particularly when abstract guidance is provided without direct answer hints. The findings suggest graphs should be leveraged not merely as external knowledge sources but as internal organizational tools that meaningfully improve both reasoning efficiency and answer quality in multi-hop question-answering tasks.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Latent Reward Steering (LRS), an inference-time framework that improves reasoning in large language models by optimizing sparse-autoencoder latent states through reward gradients. The method adaptively corrects fragile reasoning states without relying on predefined cognitive behaviors, demonstrating consistent performance improvements across multiple benchmarks.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers analyzed how language models make decisions by tracing answer scores across neural network layers in 9,000 MMLU trajectories, finding that correct answers are often unstable and that attention mechanisms better preserve correctness than MLP layers. The study reveals decision-making is a distributed process rather than a final-layer phenomenon, with implications for understanding model reliability and interpretability.
🧠 Llama
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose Credit-Attenuated Privileged Feedback (CAPF), a training mechanism that guides LLM search agents by providing verifier feedback during training to improve learning on difficult problems. The approach improves performance on open-domain QA benchmarks by leveraging information already available in reinforcement learning systems, increasing exact-match accuracy from 44.7% to 48.5% on Qwen3-4B.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers demonstrate that large language models fail to accurately predict gene expression changes in cellular perturbation experiments despite producing biologically plausible explanations. They introduce CORE, a contrastive learning method that significantly improves prediction accuracy by organizing evidence from related perturbations rather than evaluating them in isolation.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Enumerate-Conjecture-Prove (ECP), a neuro-symbolic framework that combines general LLMs and prover LLMs to formally solve mathematical answer-construction problems in Lean. The approach addresses a critical gap where current AI systems struggle with generating both candidate answers and rigorous formal proofs, achieving higher success rates than baseline LLM approaches on competition mathematics benchmarks.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce LLM-WikiRace, a benchmark that tests large language models' planning and reasoning abilities by requiring them to navigate Wikipedia links from a source to target page. While frontier models like Gemini-3 achieve superhuman performance on easy tasks, success rates plummet to 23% on hard difficulty, revealing significant limitations in long-horizon planning and recovery from failures.
🧠 GPT-5🧠 Claude🧠 Opus
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce LC-ERD, a framework for improving Large Language Model reasoning by mining high-quality supervision signals through consistency-regulated reward decomposition. The method addresses critical challenges in self-aligned LLM training by reducing label noise, providing granular step-level guidance, and preventing distributional collapse, demonstrating potential improvements in reasoning quality and generalization.
AIBearisharXiv – CS AI · Jun 26/10
🧠Researchers introduced DSR-Bench, a comprehensive benchmark testing whether large language models can reason about data structures and algorithms. Testing 13 state-of-the-art LLMs revealed significant limitations, with the best model achieving only 46% accuracy on challenging tasks, while models struggled particularly with spatial reasoning and code generation.
AIBullisharXiv – CS AI · Jun 26/10
🧠Researchers demonstrate that multi-agent debate (MAD) for large language models significantly improves when agents have diverse initial viewpoints and explicitly communicate calibrated confidence levels. The study shows that vanilla MAD often underperforms simple majority voting despite higher computational costs, but two lightweight interventions—diversity-aware initialization and confidence-modulated debate protocols—consistently outperform both baseline approaches across multiple reasoning benchmarks.
