Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract ones. Our method improves accuracy across a range of tasks, including both computation-intensive and standard benchmarks, demonstrating the effectiveness of multi-strategy distillation in achieving robust and efficient reasoning. Our project is available at https://github.com/StigLidu/DualDistill

Y et, prevailing methods, which rely on static scoring functions over learned embeddings, struggling to simultaneously capture rich semantic context and the dynamic nature of relations. T o overcome this limitation, we propose the Flow-Modulated Scoring (FMS) framework, conceptualizing a relation as a dynamic evolutionary process governed by its static semantic environment. FMS operates in two stages: it first learns context-aware entity embeddings via a Semantic Context Learning module, and then models a dynamic flow between them using a Conditional Flow-Matching module. This learned flow dynamically modulates a base static score for the entity pair. By unifying context-rich static representations with a conditioned dynamic flow, FMS achieves a more comprehensive understanding of relational semantics. Extensive experiments demonstrate that FMS establishes a new state of the art across both canonical knowledge graph completion tasks: relation prediction and entity prediction. On the standard relation prediction benchmark FB15k-237, FMS achieves a near-perfect MRR of 99.8% and Hits@1 of 99.7% using a mere 0.35M parameters, while also attaining a 99.9% MRR on WN18RR. Its dominance extends to entity prediction, where it secures a 25.2% relative MRR gain in the transductive setting and substantially outperforms all baselines in challenging inductive settings. By unifying a dynamic flow mechanism with rich static contexts, FMS offers a highly effective and parameter-efficient new paradigm for knowledge graph completion.

Imitation learning enables intelligent systems to acquire complex behaviors with minimal supervision. However, existing methods often focus on short-horizon skills, require large datasets, and struggle to solve long-horizon tasks or generalize across task variations and distribution shifts. We propose a novel neuro-symbolic framework that jointly learns continuous control policies and symbolic domain abstractions from a few skill demonstrations. Our method abstracts high-level task structures into a graph, discovers symbolic rules via an Answer Set Programming solver, and trains low-level controllers using diffusion policy imitation learning. A high-level oracle filters task-relevant information to focus each controller on a minimal observation and action space. Our graph-based neuro-symbolic framework enables capturing complex state transitions, including non-spatial and temporal relations, that data-driven learning or clustering techniques often fail to discover in limited demonstration datasets. We validate our approach in six domains that involve four robotic arms, Stacking, Kitchen, Assembly, and Towers of Hanoi environments, and a distinct Automated Forklift domain with two environments. The results demonstrate high data efficiency with as few as five skill demonstrations, strong zero- and few-shot generalizations, and interpretable decision making.

This paper presents two studies on how Brazilian children (ages 9--11) use conversational agents (CAs) for schoolwork, discovery, and entertainment, and how structured scaffolds can enhance these interactions. In Study 1, a seven-week online investigation with 23 participants (children, parents, teachers) employed interviews, observations, and Cognitive Work Analysis to map children's information-processing flows, the role of more knowledgeable others, functional uses, contextual goals, and interaction patterns to inform conversation-tree design. We identified three CA functions: School, Discovery, Entertainment, and derived ``recipe'' scaffolds mirroring parent-child support. In Study 2, we prompted GPT-4o-mini on 1,200 simulated child-CA exchanges, comparing conversation-tree recipes based on structured-prompting to an unstructured baseline. Quantitative evaluation of readability, question count/depth/diversity, and coherence revealed gains for the recipe approach. Building on these findings, we offer design recommendations: scaffolded conversation-trees, child-dedicated profiles for personalized context, and caregiver-curated content. Our contributions include the first CWA application with Brazilian children, an empirical framework of child-CA information flows, and an LLM-scaffolding ``recipe'' (i.e., structured-prompting) for effective, scaffolded learning.

Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep thinking capabilities. On the other hand, although a few works have tried to introduce Chain-of-Thought capability into PRMs, the annotation cost of CoT-PRM data is too expensive to play a stable role in various tasks. To address the above challenges, we propose VRPRM, a process reward model via visual reasoning, and design an efficient two-stage training strategy. Experimental results show that using only 3.6K CoT-PRM SFT data and 50K non-CoT PRM RL training data, VRPRM can surpass the non-thinking PRM with a total data volume of 400K and achieved a relative performance improvement of up to 118\% over the base model in the BoN experiment. This result confirms that the proposed combined training strategy can achieve higher quality reasoning capabilities at a lower data annotation cost, thus providing a new paradigm for PRM training with more efficient data utilization.

Enabling robots to efficiently search for and identify objects in complex, unstructured environments is critical for diverse applications ranging from household assistance to industrial automation. However, traditional scene representations typically capture only static semantics and lack interpretable contextual reasoning, limiting their ability to guide object search in completely unfamiliar settings. To address this challenge, we propose a language-enhanced hierarchical navigation framework that tightly integrates semantic perception and spatial reasoning. Our method, Goal-Oriented Dynamically Heuristic-Guided Hierarchical Search (GODHS), leverages large language models (LLMs) to infer scene semantics and guide the search process through a multi-level decision hierarchy. Reliability in reasoning is achieved through the use of structured prompts and logical constraints applied at each stage of the hierarchy. For the specific challenges of mobile manipulation, we introduce a heuristic-based motion planner that combines polar angle sorting with distance prioritization to efficiently generate exploration paths. Comprehensive evaluations in Isaac Sim demonstrate the feasibility of our framework, showing that GODHS can locate target objects with higher search efficiency compared to conventional, non-semantic search strategies. Website and Video are available at: https://drapandiger.github.io/GODHS

Empirical evidence shows that human behaviour often deviates from game-theoretical rationality. For instance, humans may hold unrealistic expectations about future outcomes. As the evolutionary roots of such biases remain unclear, we investigate here how reasoning abilities and cognitive biases co-evolve using Evolutionary Game Theory. In our model, individuals in a population deploy a variety of unbiased and biased level-k reasoning strategies to anticipate others' behaviour in sequential interactions, represented by the Incremental Centipede Game. Positively biased reasoning strategies have a systematic inference bias towards higher but uncertain rewards, while negatively biased strategies reflect the opposite tendency. We find that selection consistently favours positively biased reasoning, with rational behaviour even going extinct. This bias co-evolves with bounded rationality, as the reasoning depth remains limited in the population. Interestingly, positively biased agents may co-exist with non-reasoning agents, thus pointing to a novel equilibrium. Longer games further promote positively biased reasoning, as they can lead to higher future rewards. The biased reasoning strategies proposed in this model may reflect cognitive phenomena like wishful thinking and defensive pessimism. This work therefore supports the claim that certain cognitive biases, despite deviating from rational judgment, constitute an adaptive feature to better cope with social dilemmas.

3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world applications since eliminating scene-specific training requirements. However, existing zero-shot methods face challenges of spatial-limited reasoning due to reliance on single-view localization, and contextual omissions or detail degradation. To address these issues, we propose SeqVLM, a novel zero-shot 3DVG framework that leverages multi-view real-world scene images with spatial information for target object reasoning. Specifically, SeqVLM first generates 3D instance proposals via a 3D semantic segmentation network and refines them through semantic filtering, retaining only semantic-relevant candidates. A proposal-guided multi-view projection strategy then projects these candidate proposals onto real scene image sequences, preserving spatial relationships and contextual details in the conversion process of 3D point cloud to images. Furthermore, to mitigate VLM computational overload, we implement a dynamic scheduling mechanism that iteratively processes sequances-query prompts, leveraging VLM's cross-modal reasoning capabilities to identify textually specified objects. Experiments on the ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, achieving Acc@0.25 scores of 55.6% and 53.2%, surpassing previous zero-shot methods by 4.0% and 5.2%, respectively, which advance 3DVG toward greater generalization and real-world applicability. The code is available at https://github.com/JiawLin/SeqVLM.

A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and interpretability. However, it is unclear whether human understanding of this text matches the model's actual computational process. In this paper, we investigate a necessary condition for correspondence: the ability of humans to identify which steps in a reasoning text causally influence later steps. We evaluated humans on this ability by composing questions based on counterfactual measurements and found a significant discrepancy: participant accuracy was only 29%, barely above chance (25%), and remained low (42%) even when evaluating the majority vote on questions with high agreement. Our results reveal a fundamental gap between how humans interpret reasoning texts and how models use it, challenging its utility as a simple interpretability tool. We argue that reasoning texts should be treated as an artifact to be investigated, not taken at face value, and that understanding the non-human ways these models use language is a critical research direction.

Scientific reasoning is critical for developing AI scientists and supporting human researchers in advancing the frontiers of natural science discovery. However, the open-source community has primarily focused on mathematics and coding while neglecting the scientific domain, largely due to the absence of open, large-scale, high-quality, verifiable scientific reasoning datasets. To bridge this gap, we first present TextbookReasoning, an open dataset featuring truthful reference answers extracted from 12k university-level scientific textbooks, comprising 650k reasoning questions spanning 7 scientific disciplines. We further introduce MegaScience, a large-scale mixture of high-quality open-source datasets totaling 1.25 million instances, developed through systematic ablation studies that evaluate various data selection methodologies to identify the optimal subset for each publicly available scientific dataset. Meanwhile, we build a comprehensive evaluation system covering diverse subjects and question types across 15 benchmarks, incorporating comprehensive answer extraction strategies to ensure accurate evaluation metrics. Our experiments demonstrate that our datasets achieve superior performance and training efficiency with more concise response lengths compared to existing open-source scientific datasets. Furthermore, we train Llama3.1, Qwen2.5, and Qwen3 series base models on MegaScience, which significantly outperform the corresponding official instruct models in average performance. In addition, MegaScience exhibits greater effectiveness for larger and stronger models, suggesting a scaling benefit for scientific tuning. We release our data curation pipeline, evaluation system, datasets, and seven trained models to the community to advance scientific reasoning research.