AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning

Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk degrading core language competence. Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomously decide whether and which tool to invoke during the reasoning process, rather than following static tool-use strategies. AutoTIR leverages a hybrid reward mechanism that jointly optimizes for task-specific answer correctness, structured output adherence, and penalization of incorrect tool usage, thereby encouraging both precise reasoning and efficient tool integration. Extensive evaluations across diverse knowledge-intensive, mathematical, and general language modeling tasks demonstrate that AutoTIR achieves superior overall performance, significantly outperforming baselines and exhibits superior generalization in tool-use behavior. These results highlight the promise of reinforcement learning in building truly generalizable and scalable TIR capabilities in LLMs. The code and data are available at https://github.com/weiyifan1023/AutoTIR.

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains such as medicine and scientific research, where high factual precision is required. While synthetic data provides a promising avenue for augmenting domain knowledge, existing methods frequently generate redundant samples that do not align with the model's true knowledge gaps. To overcome this limitation, we propose a novel Structural Entropy-guided Knowledge Navigator (SENATOR) framework that addresses the intrinsic knowledge deficiencies of LLMs. Our approach employs the Structure Entropy (SE) metric to quantify uncertainty along knowledge graph paths and leverages Monte Carlo Tree Search (MCTS) to selectively explore regions where the model lacks domain-specific knowledge. Guided by these insights, the framework generates targeted synthetic data for supervised fine-tuning, enabling continuous self-improvement. Experimental results on LLaMA-3 and Qwen2 across multiple domain-specific benchmarks show that SENATOR effectively detects and repairs knowledge deficiencies, achieving notable performance improvements. The code and data for our methods and experiments are available at https://github.com/weiyifan1023/senator.

SetKE: Knowledge Editing for Knowledge Elements Overlap

Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs. Knowledge Editing (KE) provides a promising alternative but often overlooks the Knowledge Element Overlap (KEO) phenomenon, where multiple triplets share common elements, leading to editing conflicts. We identify the prevalence of KEO in existing KE datasets and show its significant impact on current KE methods, causing performance degradation in handling such triplets. To address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously. Experimental results demonstrate that SetKE outperforms existing methods in KEO scenarios on mainstream LLMs. Additionally, we introduce EditSet, a dataset containing KEO triplets, providing a comprehensive benchmark.

Effective Exploration Based on the Structural Information Principles

Traditional information theory provides a valuable foundation for Reinforcement Learning, particularly through representation learning and entropy maximization for agent exploration. However, existing methods primarily concentrate on modeling the uncertainty associated with RL's random variables, neglecting the inherent structure within the state and action spaces. In this paper, we propose a novel Structural Information principles-based Effective Exploration framework, namely SI2E. Structural mutual information between two variables is defined to address the single-variable limitation in structural information, and an innovative embedding principle is presented to capture dynamics-relevant state-action representations. The SI2E analyzes value differences in the agent's policy between state-action pairs and minimizes structural entropy to derive the hierarchical state-action structure, referred to as the encoding tree. Under this tree structure, value-conditional structural entropy is defined and maximized to design an intrinsic reward mechanism that avoids redundant transitions and promotes enhanced coverage in the state-action space. Theoretical connections are established between SI2E and classical information-theoretic methodologies, highlighting our framework's rationality and advantage. Comprehensive evaluations in the MiniGrid, MetaWorld, and DeepMind Control Suite benchmarks demonstrate that SI2E significantly outperforms state-of-the-art exploration baselines regarding final performance and sample efficiency, with maximum improvements of 37.63% and 60.25%, respectively.

Effective Reinforcement Learning Based on Structural Information Principles

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph's high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy's quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively.

Semi-Supervised Clustering via Structural Entropy with Different Constraints

Semi-supervised clustering techniques have emerged as valuable tools for leveraging prior information in the form of constraints to improve the quality of clustering outcomes. Despite the proliferation of such methods, the ability to seamlessly integrate various types of constraints remains limited. While structural entropy has proven to be a powerful clustering approach with wide-ranging applications, it has lacked a variant capable of accommodating these constraints. In this work, we present Semi-supervised clustering via Structural Entropy (SSE), a novel method that can incorporate different types of constraints from diverse sources to perform both partitioning and hierarchical clustering. Specifically, we formulate a uniform view for the commonly used pairwise and label constraints for both types of clustering. Then, we design objectives that incorporate these constraints into structural entropy and develop tailored algorithms for their optimization. We evaluate SSE on nine clustering datasets and compare it with eleven semi-supervised partitioning and hierarchical clustering methods. Experimental results demonstrate the superiority of SSE on clustering accuracy with different types of constraints. Additionally, the functionality of SSE for biological data analysis is demonstrated by cell clustering experiments conducted on four single-cell RNAseq datasets.

Adversarial Socialbots Modeling Based on Structural Information Principles

The importance of effective detection is underscored by the fact that socialbots imitate human behavior to propagate misinformation, leading to an ongoing competition between socialbots and detectors. Despite the rapid advancement of reactive detectors, the exploration of adversarial socialbot modeling remains incomplete, significantly hindering the development of proactive detectors. To address this issue, we propose a mathematical Structural Information principles-based Adversarial Socialbots Modeling framework, namely SIASM, to enable more accurate and effective modeling of adversarial behaviors. First, a heterogeneous graph is presented to integrate various users and rich activities in the original social network and measure its dynamic uncertainty as structural entropy. By minimizing the high-dimensional structural entropy, a hierarchical community structure of the social network is generated and referred to as the optimal encoding tree. Secondly, a novel method is designed to quantify influence by utilizing the assigned structural entropy, which helps reduce the computational cost of SIASM by filtering out uninfluential users. Besides, a new conditional structural entropy is defined between the socialbot and other users to guide the follower selection for network influence maximization. Extensive and comparative experiments on both homogeneous and heterogeneous social networks demonstrate that, compared with state-of-the-art baselines, the proposed SIASM framework yields substantial performance improvements in terms of network influence (up to 16.32%) and sustainable stealthiness (up to 16.29%) when evaluated against a robust detector with 90% accuracy.

Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs

Skin lesion segmentation is a fundamental task in dermoscopic image analysis. The complex features of pixels in the lesion region impede the lesion segmentation accuracy, and existing deep learning-based methods often lack interpretability to this problem. In this work, we propose a novel unsupervised Skin Lesion sEgmentation framework based on structural entropy and isolation forest outlier Detection, namely SLED. Specifically, skin lesions are segmented by minimizing the structural entropy of a superpixel graph constructed from the dermoscopic image. Then, we characterize the consistency of healthy skin features and devise a novel multi-scale segmentation mechanism by outlier detection, which enhances the segmentation accuracy by leveraging the superpixel features from multiple scales. We conduct experiments on four skin lesion benchmarks and compare SLED with nine representative unsupervised segmentation methods. Experimental results demonstrate the superiority of the proposed framework. Additionally, some case studies are analyzed to demonstrate the effectiveness of SLED.

Hierarchical State Abstraction Based on Structural Information Principles

State abstraction optimizes decision-making by ignoring irrelevant environmental information in reinforcement learning with rich observations. Nevertheless, recent approaches focus on adequate representational capacities resulting in essential information loss, affecting their performances on challenging tasks. In this article, we propose a novel mathematical Structural Information principles-based State Abstraction framework, namely SISA, from the information-theoretic perspective. Specifically, an unsupervised, adaptive hierarchical state clustering method without requiring manual assistance is presented, and meanwhile, an optimal encoding tree is generated. On each non-root tree node, a new aggregation function and condition structural entropy are designed to achieve hierarchical state abstraction and compensate for sampling-induced essential information loss in state abstraction. Empirical evaluations on a visual gridworld domain and six continuous control benchmarks demonstrate that, compared with five SOTA state abstraction approaches, SISA significantly improves mean episode reward and sample efficiency up to 18.98 and 44.44%, respectively. Besides, we experimentally show that SISA is a general framework that can be flexibly integrated with different representation-learning objectives to improve their performances further.

Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles

Role-based learning is a promising approach to improving the performance of Multi-Agent Reinforcement Learning (MARL). Nevertheless, without manual assistance, current role-based methods cannot guarantee stably discovering a set of roles to effectively decompose a complex task, as they assume either a predefined role structure or practical experience for selecting hyperparameters. In this article, we propose a mathematical Structural Information principles-based Role Discovery method, namely SIRD, and then present a SIRD optimizing MARL framework, namely SR-MARL, for multi-agent collaboration. The SIRD transforms role discovery into a hierarchical action space clustering. Specifically, the SIRD consists of structuralization, sparsification, and optimization modules, where an optimal encoding tree is generated to perform abstracting to discover roles. The SIRD is agnostic to specific MARL algorithms and flexibly integrated with various value function factorization approaches. Empirical evaluations on the StarCraft II micromanagement benchmark demonstrate that, compared with state-of-the-art MARL algorithms, the SR-MARL framework improves the average test win rate by 0.17%, 6.08%, and 3.24%, and reduces the deviation by 16.67%, 30.80%, and 66.30%, under easy, hard, and super hard scenarios.