6arXiv cs.LG (Machine Learning)·
SciReasoner: Multimodal foundation model for native structural reasoning across biology, chemistry, and materials science
Researchers introduce SciReasoner, a multimodal scientific foundation model that discretizes molecular coordinates, topologies, and periodic connectivities into a unified structure-aware vocabulary for reasoning over proteins, small molecules, and inorganic crystals. The model achieves state-of-the-art performance on 67 of 86 benchmarks, with notable gains in Gene Ontology prediction (F_max 0.42→0.55), retrosynthesis accuracy (0.63→0.72), and materials phase separation. Expert evaluators rated its reasoning traces as preferred or comparable to a frontier LLM in 98% of cases, suggesting meaningful interpretability alongside accuracy gains.
Related guides (2)
Related events (8)
ReaORE: Reasoning-guided progressive framework for open relation extraction using large reasoning models
ReaORE is a new framework for Open Relation Extraction (OpenRE) that uses a coarse-to-fine reasoning pipeline to identify unseen relation types between entities in unstructured text. The approach combines a relation filtering stage (using multi-aspect reasoning and embedding-based similarity) with a fine-grained comparative reasoning stage for relation prediction. The authors report that ReaORE outperforms existing baselines on two standard OpenRE benchmarks, addressing limitations of both clustering-based and direct LLM generation approaches.
Microsoft reveals MAI-Thinking-1, a from-scratch reasoning model with MoE architecture
Microsoft introduced MAI-Thinking-1, its first reasoning language model built without distillation from third-party models, comparable in size to Claude Sonnet 4.6. The model uses a mixture-of-experts architecture (1T total / 35B active parameters), was pretrained on 30 trillion tokens of primarily licensed human-generated data, and trained via reinforcement learning across specialist models for STEM, coding, and safety. It scored 97.0% on AIME 2025, placing third behind Claude Opus 4.6 and ahead of DeepSeek V3.2, and is available in private preview via Microsoft Foundry. The release marks a strategic shift as Microsoft moves to reduce dependence on OpenAI models following a renegotiated partnership in April 2026.
Systematic evaluation reveals limits of multimodal Chain-of-Thought reasoning across perception and reasoning tasks
A new arXiv paper evaluates multimodal Chain-of-Thought (CoT) reasoning across 12 tasks using 22 models (14 non-reasoning, 8 reasoning), finding that CoT is not universally beneficial: it hurts performance on perception tasks like visual grounding and object counting while helping mathematical and scientific reasoning. The study identifies a 'Look Light, Think Heavy' pattern where visual reflection consistently diminishes during reasoning chains even as verbal reflection fluctuates, pointing to deep visual introspection as a key unsolved bottleneck. Open-source multimodal reasoning models show only marginal overall gains, likely due to overemphasis on mathematical reasoning during training.
OpenMedReason: Large-scale multimodal medical reasoning corpus with 450K instances for clinical VLM training
Researchers introduce OpenMedReason, a 450K-instance open multimodal medical reasoning corpus with reasoning traces derived from human-authored biomedical literature rather than synthetic chains of thought. The dataset covers diverse medical imaging modalities and is paired with OpenMedReason-Bench, a held-out benchmark evaluating LVLMs on perception, medical knowledge, and rationale axes. Training with OpenMedReason yields a 20% average VQA accuracy improvement over base models and achieves performance within 4.2% of leading comparable-scale medical VLMs. Both the dataset and code are publicly released.
ReasoningLens: Open-source framework for hierarchical visualization and auditing of LLM reasoning chains
ReasoningLens is an open-source framework for visualizing and diagnostically auditing the long chain-of-thought traces produced by large reasoning models. It structures traces into interactive hierarchies separating high-level strategy from low-level execution, uses an agentic auditor for automated error detection, and synthesizes model-specific reasoning profiles to surface blind spots. The work targets a growing transparency problem as reasoning models produce increasingly long and opaque inference traces.
Mistral AI Releases Magistral: First Reasoning Model in Open and Enterprise Variants
Mistral AI announces Magistral, its first reasoning model, released in two variants: Magistral Small (24B parameters, open-weight, Apache 2.0) and Magistral Medium (enterprise, closed). Magistral Medium scores 73.6% on AIME2024 (90% with majority voting @64), while Magistral Small scores 70.7% (83.3% respectively). Key differentiators include native multilingual chain-of-thought reasoning across eight major languages, transparent traceable reasoning steps, and up to 10x faster token throughput in Le Chat via Flash Answers. The release is accompanied by a research paper covering training infrastructure, reinforcement learning algorithm, and novel observations for training reasoning models.
FukuyamaBench and mechanism-aware training improve LLM chemical reaction reasoning
Researchers introduce a large-scale reaction mechanism reasoning dataset and FukuyamaBench, a benchmark derived from Fukuyama's Advanced Organic Reaction Mechanism textbook, to evaluate step-by-step chemical mechanism inference in LLMs. A fine-tuned Qwen3-30B-A3B model achieves 8.3% exact pathway match on FukuyamaBench Set A, outperforming the specialized FlowER model at 5.1%. The work argues that mechanism-aware training addresses hallucinations and physical inconsistencies in current chemical LLMs, which typically focus only on coarse-grained product prediction and retrosynthesis.
Introducing GPT-Rosalind for Life Sciences Research
OpenAI has announced GPT-Rosalind, a frontier reasoning model specifically designed for life sciences applications including drug discovery, genomics analysis, protein reasoning, and scientific research workflows. The model represents a domain-specialized deployment of OpenAI's reasoning capabilities targeted at biomedical research. This is a tier-1 lab release with a focused vertical application rather than a general-purpose model launch.