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.
Related guides (1)
Related events (8)
CORA: Consistency-Oriented Reasoning Alignment addresses thinking-answer gap in multimodal RLVR
Researchers identify and analyze a systematic inconsistency between reasoning traces and final answers in RLVR-trained large vision-language models, showing the problem persists throughout GRPO training and inference. They propose CORA, which introduces a lightweight plug-and-play consistency reward model and a Hybrid Reward Advantage Splitting (HRAS) mechanism to coordinate task and consistency optimization. Experiments across multimodal reasoning benchmarks show CORA improves both task performance and reasoning faithfulness.
Open-R1: Update #1 — Open Reproduction of DeepSeek-R1
Hugging Face's Open-R1 project provides a first progress update on its open reproduction of DeepSeek-R1, a reasoning-focused language model. The update covers early training runs, dataset construction, and evaluation results aimed at replicating DeepSeek-R1's chain-of-thought reasoning capabilities. This effort is part of the broader open-weights community push to reproduce frontier reasoning models transparently.
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.
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.
CORE: Contrastive Reflection for Sample-Efficient Reasoning Improvement
CORE (Contrastive Reflection) is a non-parametric learning algorithm that improves LLM reasoning by comparing successful and unsuccessful reasoning traces to generate compact natural-language 'insights' about reasoning strategies. Across four reasoning tasks, CORE outperforms both parametric baselines (GRPO/RLVR) and non-parametric baselines (GEPA, episodic RAG, MemRL) under fixed rollout budgets, achieving comparable or better gains with as few as five training samples. The method is also more context-efficient than prompt-optimization approaches, storing learned knowledge as interpretable natural-language descriptions rather than raw traces or weight updates. The results suggest contrastive distillation of reasoning traces may be a more efficient route to self-improvement than traditional fine-tuning.
Open R1: Update #2
Hugging Face's Open R1 project releases its second progress update on the open-source replication of DeepSeek-R1's reasoning capabilities. The update likely covers training progress, dataset releases, and intermediate model checkpoints as the team works toward a fully open reproduction of the reasoning model pipeline. Open R1 is a community-driven effort to make the techniques behind frontier reasoning models accessible to researchers.
OneReason: Activating Chain-of-Thought Reasoning in Generative Recommendation Models
Researchers from the OneRec team introduce OneReason, a framework for enabling reasoning capabilities in generative recommendation models deployed across short-video, live-streaming, advertising, and e-commerce. The work identifies a key failure mode — that naive thinking-mode integration does not outperform non-thinking baselines — and diagnoses this as a deficit in two factors: itemic token perception and user behavior cognition. The proposed solution combines perception-focused pre-training, a three-level cognition-enhanced CoT format for supervised fine-tuning, and a specialize-then-unify RL training recipe.
OPERA: Perplexity-based RL alignment for open-ended reasoning tasks
OPERA (Objective Perplexity-based Reflective Alignment) proposes replacing LLM-as-a-judge reward models with intrinsic rewards derived from perplexity dynamics to stabilize RL training on open-ended tasks like creative writing. The method includes a cold-start data synthesis pipeline generating 20,000 reasoning trajectories using perplexity-prioritized rollouts. Applied to Qwen3-8B, OPERA claims state-of-the-art among open-source models on open-ended tasks, reportedly matching or exceeding Gemini 2.5 and MiniMax-M2.5 on some benchmarks.