Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong reasoning capabilities is regarded as a crucial milestone in the pursuit of Artificial General Intelligence (AGI) and has garnered considerable attention from both academia and industry. V ar-ious techniques have been explored to enhance the reasoning capabilities of LLMs, with neuro-symbolic approaches being a particularly promising way. This paper comprehensively reviews recent developments in neuro-symbolic approaches for enhancing LLM reasoning. We first present a formalization of reasoning tasks and give a brief introduction to the neuro-symbolic learning paradigm. Then, we discuss neuro-symbolic methods for improving the reasoning capabilities of LLMs from three perspectives: Symbolic LLM, LLM Symbolic, and LLM+ Symbolic . Finally, we discuss several key challenges and promising future directions. We have also released a GitHub repository including papers and resources related to this survey: https://github.com/LAMDASZ-ML/A

Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks.

Sequential data in our everyday life is often hierarchically structured.

As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom traditions, we show how four axiomatic principles can instil a resilient Wise World Model in AI systems. First, mindfulness enables self-monitoring and recalibration of emergent subgoals. Second, emptiness forestalls dogmatic goal fixation and relaxes rigid priors. Third, non-duality dissolves adversarial self-other boundaries. Fourth, boundless care motivates the universal reduction of suffering. We find that prompting AI to reflect on these principles improves performance on the AILuminate Benchmark (d=.96) and boosts cooperation and joint-reward on the Prisoner's Dilemma task (d=7+). We offer detailed implementation strategies at the level of architectures, constitutions, and reinforcement on chain-of-thought. For future systems, active inference may offer the self-organizing and dynamic coupling capabilities needed to enact Contemplative AI in embodied agents.

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning) often incur substantial computational overhead due to auxiliary models and overthinking. In this paper, we empirically reveal that the incorrect answers partially stem from verbose reasoning processes lacking correct self-fix, where errors accumulate across multiple reasoning steps. To this end, we propose Self-traced Step-wise Preference Optimization (SSPO), a pluggable RL process supervision framework that enables fine-grained optimization of each reasoning step. Specifically, SSPO requires neither auxiliary models nor stepwise manual annotations. Instead, it leverages step-wise preference signals generated by the model itself to guide the optimization process for reasoning compression. Experiments demonstrate that the generated reasoning sequences from SSPO are both accurate and succinct, effectively mitigating overthinking behaviors without compromising model performance across diverse domains and languages.

The core mechanical system is built around three stepper motors for physical manipulation, a microcontroller for hardware control, a camera and YOLO detection model for real-time cube state detection. A significant software component is the development of a user-friendly graphical user interface (GUI) designed in Unity. The initial state after detection from real-time YOLOv8 model (Precision 0.98443, Recall 0.98419, Box Loss 0.42051, Class Loss 0.2611) is virtualized on GUI. To get the solution, the system employs the Kociemba's algorithm while physical manipulation with a single degree of freedom is done by combination of stepper motors' interaction with the cube achieving the average solving time of ~2.2 minutes.

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during multi-step reasoning. Existing efforts have improved SLM performance, but typically at the cost of one or more of three key aspects: (1) reasoning capability, due to biased supervision that filters out negative reasoning paths and limits learning from errors; (2) autonomy, due to over-reliance on externally generated reasoning signals; and (3) generalization, which suffers when models overfit to teacher-specific patterns. In this paper, we introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains. To enhance reasoning capability, we propose Multi-Route Process Verification (MRPV), which contrasts both positive and negative reasoning paths to extract decisive patterns. To reduce reliance on external guidance and improve autonomy, we introduce Enabling Autonomy via Asymptotic Induction (EAAI), a training strategy that gradually fades external signals. To improve generalization, we apply guided chain-of-thought distillation to encode domain-specific rules and expert knowledge into SLM parameters, making them part of what the model has learned. Extensive experiments on both vertical and general reasoning tasks demonstrate that ReaLM significantly improves SLM performance across aspects (1)-(3) above.

Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o3 model, which emulates human-like ''thinking with image'' through iterative visual transformations and linguistic reasoning, we propose Simple o3, an end-to-end framework that integrates dynamic tool interactions (e.g., cropping, zooming, and reusing) into interleaved vision-language reasoning via supervised fine-tuning (SFT). Our approach features a scalable data synthesis pipeline that generates high-quality interleaved vision-language reasoning chains via an ''observe-reason-act'' cycle, complete with executable visual operations and rigorous verification, yielding the open-source TWI-Tools-146K dataset. Experimental results demonstrate Simple o3's superior performance on diverse benchmarks, outperforming existing approaches. By combining enhanced reasoning capabilities, Simple o3 establishes a powerful yet computationally affordable paradigm for advancing multimodal reasoning. Remarkably, we provide the first in-depth analysis of different interleaved reasoning strategies, offering insights into their impact on model performance. We found that by introducing additional visual tokens for interleaved vision-language reasoning, reusing and magnifying the original image significantly improves the model's visual reasoning and fine-grained perception, while image cropping based on precise visual grounding allows the model to effectively focus on key entities or regions, further enhancing its capabilities.

Reasoning in interactive problem solving scenarios requires models to construct reasoning threads that reflect user understanding and align with structured domain knowledge. However, current reasoning models often lack explicit semantic hierarchies, user-domain knowledge alignment, and principled mechanisms to prune reasoning threads for effectiveness. These limitations result in lengthy generic output that does not guide users through goal-oriented reasoning steps. To address this, we propose a prototype-inspired, two-phases Reasoning-Threads-Evaluation (ReT-Eval) framework, drawing inspiration from human-like reasoning strategies that emphasize structured knowledge reuse. In the first phase, semantically relevant knowledge structures are extracted from a sparse domain knowledge graph using a graph neural network and enriched with intrinsic large language model knowledge to resolve knowledge discrepancies. In the second phase, these threads are evaluated and pruned using a reward-guided strategy aimed at maintaining semantic coherence to generate effective reasoning threads. Experiments and expert evaluations show that ReT-Eval enhances user understanding and outperforms state-of-the-art reasoning models.