Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design, cross-domain generalizability, and performance guarantees, particularly as task complexity and number of agents increases. We introduces AgentGroupChat-V2, a novel framework addressing these challenges through three core innovations: (1) a divide-and-conquer fully parallel architecture that decomposes user queries into hierarchical task forest structures enabling dependency management and distributed concurrent processing. (2) an adaptive collaboration engine that dynamically selects heterogeneous LLM combinations and interaction modes based on task characteristics. (3) agent organization optimization strategies combining divide-and-conquer approaches for efficient problem decomposition. Extensive experiments demonstrate AgentGroupChat-V2's superior performance across diverse domains, achieving 91.50% accuracy on GSM8K (exceeding the best baseline by 5.6 percentage points), 30.4% accuracy on competition-level AIME (nearly doubling other methods), and 79.20% pass@1 on HumanEval. Performance advantages become increasingly pronounced with higher task difficulty, particularly on Level 5 MATH problems where improvements exceed 11 percentage points compared to state-of-the-art baselines. These results confirm that AgentGroupChat-V2 provides a comprehensive solution for building efficient, general-purpose LLM multi-agent systems with significant advantages in complex reasoning scenarios. Code is available at https://github.com/MikeGu721/AgentGroupChat-V2.
Scientific reasoning requires not only long-chain reasoning processes, but also knowledge of domain-specific terminologies and adaptation to updated findings. To deal with these challenges for scientific reasoning, we introduce RAISE, a step-by-step retrieval-augmented framework which retrieves logically relevant documents from in-the-wild corpus. RAISE is divided into three steps: problem decomposition, logical query generation, and logical retrieval. We observe that RAISE consistently outperforms other baselines on scientific reasoning benchmarks. We analyze that unlike other baselines, RAISE retrieves documents that are not only similar in terms of the domain knowledge, but also documents logically more relevant.
Reinforcement learning (RL) has become the dominant paradigm for endowing language models with advanced reasoning capabilities. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a granular understanding of their advantages is still lacking. To address this gap, we introduce a fine-grained analytic framework to dissect the impact of RL on reasoning. Our framework specifically investigates key elements that have been hypothesized to benefit from RL training: (1) plan-following and execution, (2) problem decomposition, and (3) improved reasoning and knowledge utilization. Using this framework, we gain insights beyond mere accuracy. For instance, providing models with explicit step-by-step plans surprisingly degrades performance on the most challenging benchmarks, yet RL-tuned models exhibit greater robustness, experiencing markedly smaller performance drops than their base counterparts. This suggests that RL may not primarily enhance the execution of external plans but rather empower models to formulate and follow internal strategies better suited to their reasoning processes. Conversely, we observe that RL enhances the model's capacity to integrate provided knowledge into its reasoning process, leading to performance improvements across diverse tasks. We also study difficulty, showing improved training by developing new ways to exploit hard problems. Our findings lay a foundation for more principled training and evaluation of reasoning models.
Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks. Recent automatic MAS approaches attempt to mitigate these limitations but typically necessitate a validation-set for tuning and yield static MAS designs lacking adaptability during inference. We introduce SELF-MAS, the first self-supervised, inference-time only framework for automatic MAS design. SELF-MAS employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance, without requiring a validation set. Critically, it enables dynamic agent composition and problem decomposition through meta-feedback on solvability and completeness. Experiments across math, graduate-level QA, and software engineering benchmarks, using both closed-source and open-source LLM back-bones of varying sizes, demonstrate that SELF-MAS outperforms both manual and automatic MAS baselines, achieving a 7.44% average accuracy improvement over the next strongest baseline while maintaining cost-efficiency. These findings underscore the promise of meta-level self-supervised design for creating effective and adaptive MAS.
Question Answering (QA) poses a challenging and critical problem, particularly in today's age of interactive dialogue systems such as ChatGPT, Perplexity, Microsoft Copilot, etc. where users demand both accuracy and transparency in the model's outputs. Since smaller language models (SLMs) are computationally more efficient but often under-perform compared to larger models, Knowledge Distillation (KD) methods allow for finetuning these smaller models to improve their final performance. Lately, the intermediate tokens or the so called `reasoning' traces produced by Chain-of-Thought (CoT) or by reasoning models such as DeepSeek R1 are used as a training signal for KD. However, these reasoning traces are often verbose and difficult to interpret or evaluate. In this work, we aim to address the challenge of evaluating the faithfulness of these reasoning traces and their correlation with the final performance. To this end, we employ a KD method leveraging rule-based problem decomposition. This approach allows us to break down complex queries into structured sub-problems, generating interpretable traces whose correctness can be readily evaluated, even at inference time. Specifically, we demonstrate this approach on Open Book QA, decomposing the problem into a Classification step and an Information Retrieval step, thereby simplifying trace evaluation. Our SFT experiments with correct and incorrect traces on the CoTemp QA, Microsoft Machine Reading Comprehension QA, and Facebook bAbI QA datasets reveal the striking finding that correct traces do not necessarily imply that the model outputs the correct final solution. Similarly, we find a low correlation between correct final solutions and intermediate trace correctness. These results challenge the implicit assumption behind utilizing reasoning traces for improving SLMs' final performance via KD.
Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in mathematics, coding, science, intelligent agents, and virtual assistants. In this work, we introduce an off-policy reinforcement learning algorithm, EM Policy Gradient, aimed at enhancing LLM reasoning by optimizing expected return over reasoning trajectories. We frame the reasoning task as an Expectation-Maximization (EM) optimization problem, alternating between sampling diverse rationale trajectories and performing reward-guided fine-tuning. Unlike PPO and GRPO, which rely on complex importance weights and heuristic clipping, our method provides a simpler, more principled off-policy policy gradient approach, eliminating these complexities while maintaining strong performance. We evaluate the effectiveness of EM Policy Gradient on the GSM8K and MATH (HARD) datasets, where it achieves performance comparable to or slightly surpassing the state-of-the-art GRPO, while offering additional advantages in scalability, simplicity, and reasoning conciseness. Moreover, models fine-tuned with our method exhibit cognitive behaviors, such as sub-problem decomposition, self-verification, and backtracking, highlighting its potential to enhance both the interpretability and robustness of LLM reasoning.
Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from high-resource teacher models (over 8 billion parameters) to low-resource student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113% on GSM8K and 21% on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, low-resource models to eventually serve both as both students and teachers, potentially reducing our reliance on high-resource, proprietary models.
Statistical Linkage Learning (SLL) is a part of many state-of-the-art optimizers. The purpose of SLL is to discover variable interdependencies. It has been shown that the effectiveness of SLL-using optimizers is highly dependent on the quality of SLL-based problem decomposition. Thus, understanding what kind of problems are hard or easy to decompose by SLL is important for practice. In this work, we analytically estimate the size of a population sufficient for obtaining a perfect decomposition in case of concatenations of certain unitation-based functions. The experimental study confirms the accuracy of the proposed estimate. Finally, using the proposed estimate, we identify those problem types that may be considered hard for SLL-using optimizers.
We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework enabling LLMs to autonomously improve their problem-solving capabilities through self-guided learning. By recursively generating and solving progressively simpler variants of complex problems, LADDER enables models to progressively learn through reinforcement learning how to solve harder problems. This self-improvement process is guided by verifiable reward signals, allowing the model to assess its solutions. Unlike prior approaches requiring curated datasets or human feedback, LADDER leverages the model's own capabilities to easier variants of sample questions. We demonstrate LADDER's effectiveness on mathematical integration tasks, where it improves a Llama 3B model's accuracy from 1\% to 82\% on undergraduate-level problems and enables a 7B parameter model to achieve state-of-the-art performance (70\%) on the MIT Integration Bee examination for it's model size. We also introduce TTRL (Test-Time Reinforcement Learning), a method that generates variants of test problems at inference time and applies reinforcement learning to further improve performance. By further creating and solving related problems during testing, TTRL enables the 7B model to achieve a score of 85\%, surpassing o1. These results showcase how strategic self-directed learning can achieve significant capability improvements without relying on architectural scaling or human supervision.
The concepts of linkage, building blocks, and problem decomposition have long existed in the genetic algorithm (GA) field and have guided the development of model-based GAs for decades. However, their definitions are usually vague, making it difficult to develop theoretical support. This paper provides an algorithm-independent definition to describe the concept of linkage. With this definition, the paper proves that any problems with a bounded degree of linkage are decomposable and that proper problem decomposition is possible via linkage learning. The way of decomposition given in this paper also offers a new perspective on nearly decomposable problems with bounded difficulty and building blocks from the theoretical aspect. Finally, this paper relates problem decomposition to PAC learning and proves that the global optima of these problems and the minimum decomposition blocks are PAC learnable under certain conditions.
Despite the advantage of preserving data privacy, federated learning (FL) still suffers from the straggler issue due to the limited computing resources of distributed clients and the unreliable wireless communication environment. By effectively imitating the distributed resources, digital twin (DT) shows great potential in alleviating this issue. In this paper, we leverage DT in the FL framework over non-orthogonal multiple access (NOMA) network to assist FL training process, considering malicious attacks on model updates from clients. A reputationbased client selection scheme is proposed, which accounts for client heterogeneity in multiple aspects and effectively mitigates the risks of poisoning attacks in FL systems. To minimize the total latency and energy consumption in the proposed system, we then formulate a Stackelberg game by considering clients and the server as the leader and the follower, respectively. Specifically, the leader aims to minimize the energy consumption while the objective of the follower is to minimize the total latency during FL training. The Stackelberg equilibrium is achieved to obtain the optimal solutions. We first derive the strategies for the followerlevel problem and include them in the leader-level problem which is then solved via problem decomposition. Simulation results verify the superior performance of the proposed scheme.
Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification (MTSC). Effective adaptation of LLMs for MTSC necessitates informative data representations. Existing LLM-based methods directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs. Despite their effectiveness, we reveal that these methods conceal three inherent bottlenecks: (1) they struggle to encode temporal and channel-specific information in a lossless manner, both of which are critical components of multivariate time series; (2) it is much difficult to align the learned representation space with the semantic space of the LLMs; (3) they require task-specific retraining, which is both computationally expensive and labor-intensive. To bridge these gaps, we propose TableTime, which reformulates MTSC as a table understanding task. Specifically, TableTime introduces the following strategies: (1) convert multivariate time series into a tabular form, thus minimizing information loss to the greatest extent; (2) represent tabular time series in text format to achieve natural alignment with the semantic space of LLMs; (3) design a reasoning framework that integrates contextual text information, neighborhood assistance, multi-path inference and problem decomposition to enhance the reasoning ability of LLMs and realize zero-shot classification. Extensive experiments performed on 10 publicly representative datasets from UEA archive verify the superiorities of the TableTime.
Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decomposition capabilities. To address this issue, we propose a reasoning-augmented data generation process, SRA-MCTS, which guides the model to autonomously generate high-quality intermediate reasoning paths. This creates a positive feedback loop, enabling continuous improvement. Our method operates entirely through the model itself without requiring additional supervision. By synthesizing natural language reasoning paths and translating them into executable code, the approach ensures analytical accuracy and enhances the success rate in solving complex tasks. Experimental results show that, even without additional supervisory signals, our method achieves performance improvements across different model scales, demonstrating the significant potential of self-improvement in small models. Furthermore, the method remains robust when traditional Chain-of-Thought (CoT) approaches exhibit performance degradation, with notable improvements observed in diversity metrics such as pass@10. We encourage further exploration of reasoning processes within training data to enhance the ability of language models to address complex problems. Our code and data are public at https://github.com/DIRECT-BIT/SRA-MCTS.
Integrating large language models (LLMs) like ChatGPT into computer science education offers transformative potential for complex courses such as data structures and algorithms (DSA). This study examines ChatGPT as a supplementary tool for teaching assistants (TAs), guided by structured prompts and human oversight, to enhance instruction and student outcomes. A controlled experiment compared traditional TA-led instruction with a hybrid approach where TAs used ChatGPT-4o and ChatGPT o1 to generate exercises, clarify concepts, and provide feedback. Structured prompts emphasized problem decomposition, real-world context, and code examples, enabling tailored support while mitigating over-reliance on AI. Results demonstrated the hybrid approach's efficacy, with students in the ChatGPT-assisted group scoring 16.50 points higher on average and excelling in advanced topics. However, ChatGPT's limitations necessitated TA verification. This framework highlights the dual role of LLMs: augmenting TA efficiency while ensuring accuracy through human oversight, offering a scalable solution for human-AI collaboration in education.
This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured around the context-free grammar (CFG) of the task. The CFG serves as the basis for the problem decomposition and the core premise of the instruction categories design. We propose a semi-automatic method for CFG construction with the help of Large-Language Models (LLMs). Then, we induct and generate data spanning five principal instruction categories (i.e. direction change, landmark recognition, region recognition, vertical movement, and numerical comprehension). Our analysis of different models reveals notable performance discrepancies and recurrent issues. The stagnation of numerical comprehension, heavy selective biases over directional concepts, and other interesting findings contribute to the development of future language-guided navigation systems.
Cloud manufacturing system is a service-oriented and knowledge-based one, which can provide solutions for the large-scale customized production. The service resource allocation is the primary factor that restricts the production time and cost in the cloud manufacturing customized production (CMCP). In order to improve the efficiency and reduce the cost in CMCP, we propose a new framework which considers the collaboration among services with the same functionality. A mathematical evaluation formulation for the service composition and service usage scheme is constructed with the following critical indexes: completion time, cost, and number of selected services. Subsequently, a problem decomposition based genetic algorithm is designed to obtain the optimal service compositions with service usage schemes. A smart clothing customization case is illustrated so as to show the effectiveness and efficiency of the method proposed in this paper. Finally, the results of simulation experiments and comparisons show that these solutions obtained by our method are with the minimum time, a lower cost, and the fewer selected services.
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of singe-objective combinatorial optimization (SOCO) problems and train attention models based on a single-step and deterministic greedy rollout. However, inappropriate decomposition and undesirable short-sighted behaviors of previous methods tend to induce a decline in diversity. To address the above limitation, we design a Context-aware Diversity Enhancement algorithm named CDE, which casts the neural MOCO problems as conditional sequence modeling via autoregression (node-level context awareness) and establishes a direct relationship between the mapping of preferences and diversity indicator of reward based on hypervolume expectation maximization (solution-level context awareness). Based on the solution-level context awareness, we further propose a hypervolume residual update strategy to enable the Pareto attention model to capture both local and non-local information of the Pareto set/front. The proposed CDE can effectively and efficiently grasp the context information, resulting in diversity enhancement. Experimental results on three classic MOCO problems demonstrate that our CDE outperforms several state-of-the-art baselines.
We address in this paper Reinforcement Learning (RL) among agents that are grouped into teams such that there is cooperation within each team but general-sum (non-zero sum) competition across different teams. To develop an RL method that provably achieves a Nash equilibrium, we focus on a linear-quadratic structure. Moreover, to tackle the non-stationarity induced by multi-agent interactions in the finite population setting, we consider the case where the number of agents within each team is infinite, i.e., the mean-field setting. This results in a General-Sum LQ Mean-Field Type Game (GS-MFTG). We characterize the Nash equilibrium (NE) of the GS-MFTG, under a standard invertibility condition. This MFTG NE is then shown to be $O(1/M)$-NE for the finite population game where $M$ is a lower bound on the number of agents in each team. These structural results motivate an algorithm called Multi-player Receding-horizon Natural Policy Gradient (MRNPG), where each team minimizes its cumulative cost \emph{independently} in a receding-horizon manner. Despite the non-convexity of the problem, we establish that the resulting algorithm converges to a global NE through a novel problem decomposition into sub-problems using backward recursive discrete-time Hamilton-Jacobi-Isaacs (HJI) equations, in which \emph{independent natural policy gradient} is shown to exhibit linear convergence under time-independent diagonal dominance. Numerical studies included corroborate the theoretical results.
Cooperative co-evolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the grouping stage significantly impact the performance of the optimization process. While the general separability grouping (GSG) method has overcome the limitation of previous differential grouping (DG) methods by enabling the decomposition of non-additively separable functions, it suffers from high computational complexity. To address this challenge, this article proposes a composite separability grouping (CSG) method, seamlessly integrating DG and GSG into a problem decomposition framework to utilize the strengths of both approaches. CSG introduces a step-by-step decomposition framework that accurately decomposes various problem types using fewer computational resources. By sequentially identifying additively, multiplicatively and generally separable variables, CSG progressively groups non-separable variables by recursively considering the interactions between each non-separable variable and the formed non-separable groups. Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a non-separable variable grouping method. These two methods are designed to effectively detect multiplicatively separable variables and efficiently group non-separable variables, respectively. Extensive experimental results demonstrate that CSG achieves more accurate variable grouping with lower computational complexity compared to GSG and state-of-the-art DG series designs.
The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands. Pruning has emerged as a pivotal compression strategy, introducing sparsity to enhance both memory and computational efficiency. Yet, traditional global pruning is impractical for LLMs due to scalability issues, while local pruning, despite its efficiency, leads to suboptimal solutions. Addressing these challenges, we propose SparseLLM, a novel framework that redefines the global pruning process into manageable, coordinated subproblems, allowing for resource-efficient optimization with global optimality. SparseLLM's approach, which conceptualizes LLMs as a chain of modular functions and leverages auxiliary variables for problem decomposition, not only facilitates a pragmatic application on LLMs but also demonstrates significant performance improvements, particularly in high-sparsity regimes where it surpasses current state-of-the-art methods.