Multi-Agent Reasoning

Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex interpersonal interactions. To support structured analysis, we introduce MOTOR-Bench, a carefully-designed benchmark with a real-world dataset MOTOR-dataset, containing 1,440 multimodal video clips in collaborative learning scenarios, reflecting key real-world data challenges including natural class imbalance, visual noise, and domain-specific language. Each sample is labeled by educational experts based on self-regulated learning theory. We further evaluate several state-of-the-art multimodal large language models and multi-agent systems in a zero-shot setting on our MOTOR-Bench. However, their performance on this task remains limited, suggesting that existing methods still struggle with structured reasoning from observable behavior to deeper mental states. To address this challenge, we propose a reasoning multi-agent framework, named MOTOR-MAS. It coordinates multiple agents through a structured agent coordination mechanism to infer explicit behaviors, internal cognitions, and psychological emotions. Experimental results show that our MOTOR-MAS outperforms the best single-model benchmark by 15.93 points in Macro-F1 scores for the three labels of behavior, cognition, and emotion, and outperforms the general multi-agent benchmark by 10.2 points in internal cognition prediction.

Closed-loop traffic simulation requires agents that are both scalable and behaviorally realistic. Recent self-play reinforcement learning approaches demonstrate strong scalability, but their equilibrium strategies fail to capture the socially aware behaviors of real human drivers. We propose a hierarchical architecture that goes beyond self-play by combining high-level multi-agent interaction reasoning with low-level continuous trajectory realization. Specifically, a Stackelberg-style Multi-Agent Reinforcement Learning (MARL) module generates interaction-aware intention commands. These commands condition a low-level continuous motion module, translating the strategic intent into physically consistent, scene-responsive control sequences. To mitigate distribution shift in closed-loop deployment, we introduce a hybrid co-training scheme combining MARL with auxiliary recovery supervision. Experiments on a SUMO-based urban network demonstrate that the proposed framework achieves superior control smoothness and safety compared to self-play and passive imitation baselines, while maintaining competitive traffic efficiency.

Multi-agent reasoning has shown promise for improving the problem-solving ability of large language models by allowing multiple agents to explore diverse reasoning paths. However, most existing multi-agent methods rely on inference-time debate or aggregation, which can be vulnerable to incorrect peer influence and biased consensus. Moreover, the agents themselves remain static, as their underlying reasoning skills do not evolve across tasks. In this paper, we introduce \textbf{AgentPSO}, a particle-swarm-inspired framework for evolving multi-agent reasoning skills. AgentPSO treats each agent as a particle-like reasoner whose state is a natural-language skill and whose velocity is a semantic update direction, iteratively guiding agents toward higher-performing skill configurations. Across training iterations, each agent updates its skill by combining its previous velocity, personal-best skill, global-best skill, and a self-reflective direction derived from peer reasoning trajectories. This enables agents to learn reusable reasoning behaviors by drawing on their own experience and on the strongest skills found by the population, without updating the parameters of the backbone language model. Experiments on mathematical and general reasoning benchmarks show that AgentPSO improves over static single-agent skills and test-time-only multi-agent reasoning baselines. The evolved skills further transfer across benchmarks and to another backbone model, suggesting that AgentPSO captures reusable reasoning procedures rather than merely optimizing benchmark-specific prompts. Code is publicly available at https://github.com/HYUNMIN-HWANG/AgentPSO/.

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches predominantly rely on model-centric strategies, such as architectural modifications and data scaling, which are costly and offer limited interpretability. Alternative methods leveraging external tools or prompting techniques (e.g., chain-of-thought) are often fragmented and lack a unified framework. In this paper, we propose MAS-Algorithm, a systematic multi-agent workflow for algorithmic problem solving inspired by the practices of competitive programmers and algorithm engineers. Our framework decomposes the end-to-end solving process into modular stages, enabling structured reasoning, tool integration, and flexible coordination among agents. The design emphasizes both rigor and extensibility, allowing it to generalize across diverse problem types. Experimental results on a self-constructed benchmark demonstrate consistent improvements across multiple Qwen series models, achieving an average gain of 6.48% in acceptance rate. In contrast, parameter-efficient fine-tuning on the same data yields only a marginal improvement of 0.89%. We further observe a 4.72% gain on LiveCodeBench-Pro, along with consistent improvements across additional accuracy and efficiency metrics. Beyond performance gains, we conduct comprehensive analyses to better understand the reasoning process within the workflow, including error patterns and cross-scenario behaviors. We further perform customized replacement and ablation studies to explore the upper bound of the framework, showing that individual agents can contribute improvements of up to 27.7%. These results highlight the strong potential of MAS-Algorithm for advancing AI-driven algorithmic reasoning.

We investigate the belief revision problem in epistemic planning, i.e., what will be the beliefs of all agents in a multi-agent system after an agent gains the belief in some state property. Based on the standard representation in epistemic planning of agents' beliefs via a single multi-agent Kripke model, we generalize the classical AGM belief revision postulates to the multi-agent setting, with the aim to provide a formal framework for evaluating dynamic epistemic reasoning frameworks in which the beliefs of all agents as the result of actions are computed. As an example of a simple operator that satisfies all of the generalized AGM postulates, we present generalized full-meet multi-agent belief revision. We moreover define a generalization of the standard postulates for iterated revision, present a more sophisticated, event model based revision operator, and discuss the potential issues in defining an epistemic operator on Kripke models that can satisfy all of the generalized postulates for iterated multi-agent belief revision.

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key for real-world applications with resource constraints. We provide a systematic analysis of the inference scaling strategies self-consistency, self-refinement, multi-agent debate, and mixture-of-agents, to study their computational performance tradeoffs. We evaluate methods on two reasoning benchmarks (MMLU-Pro, BBH) and include extensive parameter configurations (e.g., scaling the number of parallel predictions, agents, and debate rounds) across different model sizes. Across 34 configurations and over 100 evaluations, we compute the Pareto-optimal front to select methods that achieve the best accuracy with the lowest computational budget. Notably, inference scaling improves accuracy by up to +7.1% points over chain-of-thought at the highest evaluated budgets (20x the CoT compute budget) on MMLU-Pro. With an equal computing budget, debate and mixture-of-agents outperform self-consistency by 1.3% and 2.7% points, respectively. While self-consistency saturates earlier, multi-agent gains persist, particularly on more complicated tasks. We identify a simple multi-agent design guideline: mixture-of-agents is most efficient when the number of parallel generations exceeds the number of sequential aggregations.

Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a single context window comes with a well-known cost: as tool specifications and observational traces accumulate, the effective context available for each decision shrinks, and end-to-end reliability suffers. We present a multi-agent system (MAS) prototype for hydrodynamics in which specialized agents are coordinated through a Layer Execution Graph (LEG). A planner agent constructs query-specific execution topologies from natural-language routing heuristics that capture domain knowledge without hard-coding it as rigid control logic; specialist agents operate under strict tool allowlists and occupy complementary data-class roles. Between layers, consolidator agents fuse parallel outputs into concise briefs, and a reporter agent synthesizes the final response, while the runtime logs provenance for every tool invocation to support auditability. All benchmarks, ablations, and stress tests use Claude Sonnet~4.6 as the backbone model for both specialist and general-purpose agents. Evaluated on 37 queries spanning six complexity categories, the prototype achieves 93.6% factual precision with a 100% pass rate. Accuracy remains above 90% across runs from single-threaded to five independent parallel tracks, and under simulated loss of individual data sources the system degrades gracefully, still returning substantive partial answers. Together, these results suggest that planner-guided, graph-structured multi-agent orchestration can meaningfully alleviate the context-saturation bottlenecks that constrain monolithic single-agent architectures.

Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an agentic AI framework that replaces the traditional signal then execute paradigm with a fully autonomous deliberative loop in which multiple specialized Large Language Model agents reason, negotiate, and act in concert - without any offline training or human intervention. The framework proposes four architectural contributions: (i) an Adaptive Z-Score Trigger Engine that acts as a cognitive resource allocator, gating LLM inference exclusively on statistically anomalous market conditions; (ii) a Sequential Deliberative Pipeline - the core agentic contribution - in which an Analyst agent, a Risk Manager agent, and an Executor agent form a structured reasoning chain governed by typed JSON contracts and a deterministic hard-gate safety layer; (iii) an Inference Gating Protocol, a mutex-based cognitive resource scheduler that serializes concurrent agent activations and ensures fully reproducible audit trails; and (iv) a Correlation-Break Diversification composite score that operationalizes portfolio-level idiosyncratic signal prioritization within individual agent reasoning. Validated over a five-day autonomous dry-run session under live market conditions, the framework demonstrates operational correctness of the deliberative pipeline, achieving 157 zero-intervention invocations across 76 assets with an 11.5% agentic friction rate that confirms non-trivial inter-agent negotiation. This preliminary proof-of-concept establishes the feasibility of training-free, deterministic safety-constrained multi-agent orchestration in financial decision loops, with statistically robust performance evaluation and execution cost modeling deferred to extended live deployment.

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and bias; (2) Scalability, as reasoning complexity creates bottlenecks; (3) Opacity, as hidden auditing erodes trust; and (4) Privacy, as exposed reasoning traces risk model theft. We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations: (i) Hierarchical Directed Acyclic Graphs (HDAGs) that decompose Chain-of-Thought reasoning into five abstraction levels for parallel distributed auditing; (ii) the DAAN protocol, which projects multi-agent interactions into Causal Interaction Graphs (CIGs) for deterministic root-cause attribution; and (iii) a multi-tier consensus mechanism among computational checkers, LLM evaluators, and human experts with stake-weighted voting that guarantees correctness under 30% adversarial participation. We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses. All decisions are recorded on-chain, while privacy-by-design segmentation prevents reconstruction of proprietary logic. Across multiple LLMs and benchmarks, TRUST attains 72.4% accuracy (4-18% above baselines) and remains resilient against 20% corruption. DAAN reaches 70% root-cause attribution (vs. 54-63% for standard methods) with 60% token savings. Human studies validate the design (F1 = 0.89, Brier = 0.074). The framework supports (A1) decentralized auditing, (A2) tamper-proof leaderboards, (A3) trustless data annotation, and (A4) governed autonomous agents, pioneering decentralized AI auditing for safe, accountable deployment of reasoning-capable systems.

We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four LLM families in the cooperative card game Hanabi, we establish four findings. First, integration architecture determines whether belief graphs provide value: as prompt context, graphs are decorative for strong models and beneficial only for weak models on 2nd-order Theory of Mind (80% vs 10%, p<0.0001, OR=36.0); when graphs gate action selection through ranked shortlists, they become structurally essential even for strong models (100% vs 20% on 2nd-order ToM, p<0.001). Second, we identify "Planner Defiance," a model-family-specific failure where LLMs override correct planner recommendations at partial competence (90% override, replicated N=20); Gemini models show near-zero defiance while Llama 70B shows 90%, and models distinguish factual context (deferred to) from advisory recommendations (overridden). Third, full-game evidence confirms inter-agent conventions (+128% over baseline, p=0.003) outperform all single-agent interventions, and individual belief-graph components must be combined to produce gains. Fourth, preliminary scaling analysis (N=10/cell, exploratory) suggests graph depth has diminishing returns: shallow graphs provide the best cost-benefit ratio, while deeper ToM graphs appear harmful at larger player counts (-1.5 pts at 5-player, p=0.029).

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.

Long-form video understanding remains fundamentally challenged by pervasive spatiotemporal redundancy and intricate narrative dependencies that span extended temporal horizons. While recent structured representations compress visual information effectively, they frequently sacrifice temporal coherence, which is critical for causal reasoning. Meanwhile, existing multi-agent frameworks operate through rigid, pre-defined workflows that fail to adapt their reasoning strategies to question-specific demands. In this paper, we introduce HiCrew, a hierarchical multi-agent framework that addresses these limitations through three core contributions. First, we propose a Hybrid Tree structure that leverages shot boundary detection to preserve temporal topology while performing relevance-guided hierarchical clustering within semantically coherent segments. Second, we develop a Question-Aware Captioning mechanism that synthesizes intent-driven visual prompts to generate precision-oriented semantic descriptions. Third, we integrate a Planning Layer that dynamically orchestrates agent collaboration by adaptively selecting roles and execution paths based on question complexity. Extensive experiments on EgoSchema and NExT-QA validate the effectiveness of our approach, demonstrating strong performance across diverse question types with particularly pronounced gains in temporal and causal reasoning tasks that benefit from our hierarchical structure-preserving design.

Understanding visual scenes requires not only recognizing objects but also reasoning about their spatial relationships. Unlike general vision-language tasks, spatial reasoning requires integrating multiple inductive biases, such as 2D appearance cues, depth signals, and geometric constraints, whose reliability varies across contexts. This suggests that effective spatial reasoning requires spatial adaptability: the ability to flexibly coordinate different reasoning strategies depending on the input. However, most existing approaches rely on a single reasoning pipeline that implicitly learns a fixed spatial prior, limiting their ability to adapt under distribution changes. Multi-agent systems offer a promising alternative by aggregating diverse reasoning trajectories, but prior attempts in spatial reasoning primarily employ homogeneous agents, restricting the diversity of inductive biases they can leverage. In this work, we introduce SpatiO, a heterogeneous multi-agent framework for spatial reasoning that coordinates multiple vision-language specialists with complementary inductive biases. To enable effective collaboration, we propose Test-Time Orchestration (TTO), an calibration mechanism that dynamically evaluates and reweights agents based on their observed reliability during inference, without modifying model parameters. Extensive experiments on diverse spatial reasoning benchmarks, including 3DSRBench, STVQA-7k, CV-Bench, and Omni3D-Bench, demonstrate that SpatiO consistently improves spatial reasoning performance over both closed-source and open-source baselines. The project page is available at https://cy-h1329.github.io/spatio/.

Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing. While such role-playing effectively leverages domain expert knowledge, we find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry (AOA). Specifically, an agent acting as an actor (during self-reflection) tends to attribute failures to external factors, whereas an observer (during mutual auditing) attributes the same errors to internal faults. We quantify this using our new Ambiguous Failure Benchmark, which reveals that simply swapping perspectives triggers the AOA effect in over 20% of cases for most models. To tame this bias, we introduce ReTAS (Reasoning via Thesis-Antithesis-Synthesis), a model trained through dialectical alignment to enforce perspective-invariant reasoning. By integrating dialectical chain-of-thought with Group Relative Policy Optimization, ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus. Experiments demonstrate that ReTAS effectively mitigates attribution inconsistency and significantly improves fault resolution rates in ambiguous scenarios.

Social deduction games such as Mafia present a unique AI challenge: players must reason under uncertainty, interpret incomplete and intentionally misleading information, evaluate human-like communication, and make strategic elimination decisions. Unlike deterministic board games, success in Mafia depends not on perfect information or brute-force search, but on inference, memory, and adaptability in the presence of deception. This work presents the design and evaluation of Revac-8, an AI agent developed for the Social Deduction track of the MindGames Arena competition, where it achieved first place. The final agent evolved from a simple two-stage reasoning system into a multi-module architecture that integrates memory-based player profiling, social-graph analysis of accusations and defenses, and dynamic tone selection for communication. These results highlight the importance of structured memory and adaptive communication for achieving strong performance in high-stakes social environments.

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.

Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since graphs are naturally more complex in topology and often require systematic multi-step reasoning, especially on larger graphs. Motivated by this gap, we propose GraphDC, a Divide-and-Conquer multi-agent framework for scalable graph algorithm reasoning. Specifically, inspired by Divide-and-Conquer design, GraphDC decomposes an input graph into smaller subgraphs, assigns each subgraph to a specialized agent for local reasoning, and uses a master agent to integrate the local outputs with inter-subgraph information to produce the final solution. This hierarchical design reduces the reasoning burden on individual agents, alleviates computational bottlenecks, and improves robustness on large graph instances. Extensive experiments show that GraphDC consistently outperforms existing methods on graph algorithm reasoning across diverse tasks and scales, especially on larger instances where direct end-to-end reasoning is less reliable.

The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to generalize beyond their training distributions. To address this, we propose DVAR (Debate-based Video Authenticity Reasoning), a training-free framework that reformulates video detection as a structured multi-agent forensic reasoning process. Moving beyond the paradigm of pattern matching, DVAR orchestrates a competition between a Generative Hypothesis Agent and a Natural Mechanism Agent. Through iterative rounds of cross-examination, these agents defend their respective explanations against abnormal evidence, driving a logical convergence where the truth emerges from rigorous stress-testing. To adjudicate these conflicting claims, we apply Occam's Razor through the Minimum Description Length (MDL) framework, defining an Explanatory Cost to quantify the "logical burden" of each reasoning path. Furthermore, we integrate GenVideoKB, a dynamic knowledge repository that provides high-level reasoning heuristics on generative boundaries and failure modes. Extensive experiments demonstrate that DVAR achieves competitive performance against supervised state-of-the-art methods while exhibiting superior generalization to unseen generative architectures. By transforming detection into a transparent debate, DVAR provides explicit, interpretable reasoning traces for robust video authenticity assessment.

We propose a federated learning-like framework, Federation over Text (FoT), that enables multiple clients solving different tasks to collectively generate a shared library of metacognitive insights by iteratively federating their local reasoning processes without sharing actual problem instances or task instructions. Instead of federation over gradients (e.g., as in distributed training), FoT operates at the semantic level without any gradient optimization or supervision signal. Iteratively, each client runs an LLM agent that does local thinking and self-improvement on their specific tasks independently, and shares reasoning traces with a central server, which aggregates and distills them into a cross-task (and cross-domain) insight library that existing and future agents can leverage to improve performance on related tasks. Experiments show that FoT improves reasoning effectiveness and efficiency across a wide range of challenging applications, including mathematical problem solving, cross-domain collaboration, real-world daily tasks, and machine learning research insight discovery. Specifically, it improves average performance scores by 25% while reducing the reasoning tokens by 4% across the first three applications. In the research insight discovery application, FoT is able to generate insights that cover over 80% of the major contributions in the subsequent papers.

Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several subtasks, has not been adequately studied. Due to the complexity of the astronomical imaging process, both world-class astronomical organizations, such as NASA, and expert enthusiasts devote a great deal of time and effort. This is because the processes in astronomical imaging have complex underlying correlations that significantly influence one another, making the quality diagnosis and error localization of astronomical images challenging. To address this problem, we propose AstroVLM, a collaborative multi-agent system for diagnosing the quality of astronomical images. Experiment results show that AstroVLM outperforms all baselines on real-world astronomical imaging quality diagnosis tasks, providing a reference for language models to handle complicated multi-process tasks.

LLM-driven multi-agent frameworks address complex reasoning tasks through multi-role collaboration. However, existing approaches often suffer from reasoning instability, where individual agent errors are amplified through collaboration, undermining overall performance. Current research mainly focuses on enhancing high-capability agents or suppressing unreliable outputs to improve framework effectiveness, while systematic identification and reinforcement of performance-limiting agents receive less attention. To address this gap, we propose WORC, a \underline{w}eak-link \underline{o}ptimization framework for multi-agent \underline{r}easoning and \underline{c}ollaboration, grounded in the weak-link principle. WORC follows a two-stage workflow. In the weak agent localization stage, task features are constructed, and a meta-learning-based weight predictor trained on optimal configurations identified by swarm intelligence algorithms (SIAs) enables zero-shot mapping from these features to agent performance weights, where the agent with the lowest predicted weight is identified as the weak agent. In the weak-link optimization stage, an uncertainty-driven allocation strategy assigns additional reasoning budgets to weak agents, with lower predicted weights leading to larger repeated-sampling quotas to compensate for reliability deficiencies. Experimental results show that WORC achieves an average accuracy of 82.2% on reasoning benchmarks while improving framework stability and cross-architecture generalization, suggesting that compensating for weak links, rather than reinforcing strengths alone, enhances the robustness of multi-agent systems.

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

Complex question answering across text, tables and images requires integrating diverse information sources. A framework supporting specialized processing with coordination and interpretability is needed. We introduce DeALOG, a decentralized multi-agent framework for multimodal question answering. It uses specialized agents: Table, Context, Visual, Summarizing and Verification, that communicate through a shared natural-language log as persistent memory. This log-based approach enables collaborative error detection and verification without central control, improving robustness. Evaluations on FinQA, TAT-QA, CRT-QA, WikiTableQuestions, FeTaQA, and MultiModalQA show competitive performance. Analysis confirms the importance of the shared log, agent specialization, and verification for accuracy. DeALOG, provides a scalable approach through modular components using natural-language communication.

Large Language Model (LLM) agents deployed in complex real-world scenarios increasingly operate as spatially distributed entities. However, this physical dispersion constrains agents to limited local perception and finite temporal horizons. We characterize this bottleneck as spatiotemporal partial observability, where spatial and temporal limitations are fundamentally coupled: resolving spatial conflicts requires temporal reasoning about neighbors' future actions, while temporal planning requires spatial context beyond local perception. To bridge this gap, we introduce MACRO-LLM, LLM-empowered multi-agent collaborative reasoning under spatiotemporal partial observability. The architecture interleaves spatial and temporal reasoning within each decision cycle via three interdependent modules: (1) the CoProposer mitigates temporal uncertainty by verifying candidate actions via predictive rollouts; (2) the Negotiator overcomes spatial myopia by resolving conflicts through mean-field statistical aggregation, grounded in the CoProposer's rollout rewards; and (3) the Introspector closes the reasoning loop by analyzing environmental drift and attributing performance changes to refine strategies. Extensive evaluations on two complex long-horizon tasks, cooperative platoon planning and pandemic control, demonstrate that our framework enables robust coordination under spatiotemporal partial observability.

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter, manageable ones, recent multi-agent paradigms offer a promising near-term solution to this problem. However, the fundamental capacities of such systems are poorly understood. In this work, we propose a theoretical framework to analyze the expressivity of multi-agent systems. We apply our framework to three algorithmic families: state tracking, recall, and $k$-hop reasoning. We derive bounds on (i) the number of agents required to solve the task exactly, (ii) the quantity and structure of inter-agent communication, and (iii) the achievable speedups as problem size and context scale. Our results identify regimes where communication is provably beneficial, delineate tradeoffs between agent count and bandwidth, and expose intrinsic limitations when either resource is constrained. We complement our theoretical analysis with a set of experiments on pretrained LLMs using controlled synthetic benchmarks. Empirical outcomes confirm the tradeoffs between key quantities predicted by our theory. Collectively, our analysis offers principled guidance for designing scalable multi-agent reasoning systems.