Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks. Existing methods for multi-quadruped manipulation typically focus on predefined or closed task families, often relying on multi-agent reinforcement learning (MARL) to train task-specific coordination policies. However, such methods struggle in open-ended continual learning settings, where tasks arrive sequentially and robots are expected to acquire new coordination skills while reusing previously learned ones without catastrophic forgetting. To address this challenge, we propose Conquer, a semantic skill-library framework that formulates continual multi-quadruped coordination as a retrieve-adapt-update process. First, to accommodate varying team sizes across tasks, we design a team-structured Self-Allies-Goal (SAG) backbone that supports variable-cardinality robot teams by explicitly modeling each robot's own state, teammate context, and task goal. For each incoming task, Conquer constructs a task-level semantic descriptor from pre-execution information and retrieves a relevant skill from the library for adaptation. After successful execution, Conquer updates the skill library by extracting trajectory-level semantic descriptors and organizing them according to semantic distance, thereby enabling continual skill accumulation and cross-task knowledge transfer. Simulation experiments show that Conquer achieves a final average success rate of 95.6

While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Existing acceleration methods typically require policy retraining or costly online interactions, limiting their scalability for large-scale foundation models. In this paper, we propose Speedup Patch (SuP), a lightweight, policy-agnostic framework that enables plug-and-play acceleration using solely offline data. SuP introduces an external scheduler that adaptively downsamples action chunks provided by embodied policies to eliminate redundancies. Specifically, we formalize the optimization of our scheduler as a Constrained Markov Decision Process (CMDP) aimed at maximizing efficiency without compromising task performance. Since direct success evaluation is infeasible in offline settings, SuP introduces World Model based state deviation as a surrogate metric to enforce safety constraints. By leveraging a learned world model as a virtual evaluator to predict counterfactual trajectories, the scheduler can be optimized via offline reinforcement learning. Empirical results on simulation benchmarks (Libero, Bigym) and real-world tasks validate that SuP achieves an overall 1.8x execution speedup for diverse policies while maintaining their original success rates.

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.

Full-proof autoformalization bridges extensive mathematical proofs in natural language with formally validated reasoning, offering a pathway to elevate the ceiling of verifiable mathematical reasoning. Unlike statement-level formalization, proof autoformalization is a long-horizon challenge requiring coordination of claims, contexts, and dependencies across many proof steps, yet has only recently come under focused study. Current approaches either rely on costly model training or apply excessive, unguided repair at inference time. To this end, we introduce ToMap, a multi-agent framework that structures proof autoformalization as a Decomposer-Formalizer-Prover pipeline with efficient test-time optimization guided by formal verification and semantic rubrics for proof quality. Rather than distributing test-time compute across all agents, we perform bottleneck analysis and identify the Decomposer as the critical bottleneck: the quality of its atomic, self-contained proof units directly determines whether downstream agents can successfully formalize and prove each step. ToMap therefore treats the Formalizer and Prover as downstream executors and efficiently focuses test-time compute on Decomposer refinement. This refinement follows a loop inspired by GEPA, evolving prompts over candidate decompositions and using formal verification progress together with semantic proof rubrics to define a Pareto frontier that guides the next decomposition update. Experiments on ProofFlowBench show that ToMap improves over the best previous method by 19.0

Humans exhibit remarkable motor agility, enabling a wide range of dynamic skills such as running and jumping, which highlights the great potential of humanoid robots for athletic locomotion. Among athletic sports, long rope skipping requires two rope turners to cooperatively swing the rope while adapting to a player under different jumping rhythms, making it a meaningful yet challenging task for humanoid robots. Although existing methods for humanoid sports have achieved success in single-agent and interaction-free settings, such as running, dancing, and parkour, task scenarios that require precise coordination among multiple participants remain largely unexplored. To this end, we propose Marope, a multi-agent reinforcement learning (MARL) framework for cooperative long rope skipping with multiple humanoid robots. Specifically, Marope adopts a hierarchical reinforcement learning framework for policy training. At the lower level, it learns decentralized rope manipulation policies through MARL, while at the upper level, a centralized scheduling policy is trained to coordinate the execution of the lower-level policies. To improve generalization across different player behavioral styles, Marope further incorporates diverse jumping policies into cooperative game training. We evaluate our approach on Unitree G1 humanoid robots in both simulation and real-world settings. Experimental results demonstrate that Marope outperforms various baselines, achieving more efficient and stable rope manipulation as well as more robust and adaptable cooperation with varied players.

Language model self-improvement (LMSI) techniques have recently gained significant attention as they improve language models without requiring external supervision. A notable approach is reinforcement learning from AI feedback (RLAIF), which trains a reward model based on AI preference data and employs reinforcement learning (RL) algorithm to train the language model. However, RLAIF relies on a heuristic assumption that the AI model is able to provide effective feedback, which requires the language model to possess solid capability. In this paper, we present a novel LMSI method, Reinforcement Learning Contemplation (RLC). We disclose that it is simpler for language models to evaluate the text than to generate it, even for small models under 1B parameters. Leveraging the gap between the evaluation and generation, RLC evaluates the generated answers and updates language model using RL to maximize self-evaluation scores. We demonstrate the effectiveness of RLC on a wide range of challenging tasks, including reasoning, summarization, conditioned generation and emotion recognition, resulting in a increase in the answering accuracy (31.23% -> 37.09%) for BigBench-hard reasoning tasks, and a rise in BERTScore for CNN/Daily Mail summarization tasks. In addition, RLC can be applied to models of different sizes (80M to 3B) and model structures (FLAN-T5, LLAMA-3.2 and QWEN-2.5), showcasing its broad applicability. We further verify that when training on larger scale of dataset, RLC improves language model's evaluation and generation ability on unseen tasks simultaneously, enabling a general capability improvement without external supervision.

Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized language models with strong optimization generalization capabilities. The code is available at https://github.com/Hsiang-1/MiniOpt.

The *Learnware* paradigm aims to help users solve machine learning tasks by leveraging existing well-trained models rather than starting from scratch. A learnware comprises a submitted model paired with a *specification* sketching its capabilities. For an open platform with continuously uploaded models, these specifications are essential to enabling users to identify helpful models, eliminating the requirement for prohibitively costly per-model evaluations. In previous research, specifications based on privacy-preserving reduced sets succeed in enabling learnware identification through distribution matching, but suffer from high sample complexity for learnwares from high-dimensional, unstructured data like images or text. In this paper, we formalize **Pa**rameter **Ve**ctor (PAVE) specification for learnware identification, which utilizes the changes in pre-trained model parameters to inherently encode the model capability and task requirements, offering an effective solution for these learnwares. Theoretically, from the neural tangent kernel perspective, we establish a tight connection between PAVE and prior specifications, providing a theoretical explanation for their shared underlying principles. We further approximate the parameter vector in a low-rank space and analyze the approximation error bound, highly reducing the computational and storage overhead. Extensive empirical studies demonstrate that PAVE specification excels at identifying CV and NLP learnwares for reuse on given user tasks, and succeeds in identifying helpful learnwares from open learnware repository with corrupted model quality for the first time. Reusing identified learnware to solve user tasks can even outperform user-fine-tuned pre-trained models in data-limited scenarios.

Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does not: a usable education-facing model is supposed to be accurate, safe under sensitive prompts, instructionally useful, and aligned with pedagogical goals at the same time. Existing benchmarks evaluate these requirements largely in isolation, so none assesses education-facing suitability as an integrated profile. We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol, combining curated public sources with newly synthesized safety and cultivation data. We evaluate nine models, seven frontier general-purpose systems and two education-specialized variants, and report three findings. First, module-level profiles are more informative than a single aggregate: the top six models are statistically indistinguishable on overall score, yet their module leaders differ substantially, and safety is anti-correlated with practical teaching (r = -0.83). Second, the Chinese-developed models lead the safety module, the most discriminative in the suite; this advantage is largest on region-specific normative content and narrows, but does not vanish, on universal-harm content. Third, the two education-specialized models lead neither education module, and on High-Level Cultivation all models share a systematic blind spot: on the structured judgment task they converge on the same non-reference option, favoring pedagogical style over fit to the stated goal, so the module scores uniformly low and does not separate models. This raises, but does not resolve, whether domain post-training keeps pace with frontier systems on education tasks.

Parameter sharing is a widely used technique in Multi-Agent Reinforcement Learning (MARL) that enhances sample efficiency by equipping agents with a unified policy. While effective in homogeneous settings, it often struggles in heterogeneous environments where agents possess diverse capabilities. Conversely, learning customized policies for agents can resolve knowledge conflicts but significantly hinders knowledge transfer, thereby reducing learning efficiency. Existing approaches attempt to balance this trade-off using clustering or agent-specific masks, but they typically rely on strong environment-specific priors and struggle in settings where the team exhibits multi-modal policies. To address these limitations, we propose Dspic, an efficient shared-policy algorithm grounded in the maximum entropy framework. Specifically, Dspic employs self-supervised learning to extract discriminative role embeddings for each agent. These embeddings guide a complete division of the observation space, providing a theoretical guarantee for the optimality of parameter sharing. Furthermore, to handle the increased observation complexity and diversity resulting from this division, Dspic incorporates a diffusion policy, enhancing the capacity to model complex action distributions while enabling efficient learning. Extensive experiments on MaMuJoCo, SMAC, SMACv2, and LBF demonstrate that Dspic achieves superior sample efficiency while maintaining asymptotic optimality.

World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models, latent imagination models, future-video predictors, interactive neural simulators, latent predictive representations, and synthetic-data engines. Evaluation has broadened along with the term. Recent papers measure video realism, perceptual similarity, instruction following, physical plausibility, policy ranking, executability, planning success, and downstream policy improvement. This produces both metric diversity and a recurring problem of claim/evidence mismatch: papers sometimes make a stronger claim about what their model is useful for than their evaluation can establish. This paper surveys the recent literature and argues that, for models presented as world models for embodied decision-making, the more decisive issue is not whether the model generates visually convincing videos, but whether it supports reliable interventional reasoning, policy evaluation, planning, and policy optimization under intervention, policy-induced distribution shift, and long-horizon rollout. We organize the survey using an L0–L7 ladder spanning visual plausibility to policy optimization utility, noting that the levels cut across several orthogonal axes and so form an evidential hierarchy rather than a single scalar. The framework foregrounds interventional action fidelity, closed-loop rollout validity, reward/value prediction, policy-ranking agreement, optimization lift, model exploitability, and uncertainty calibration, with a minimal feasible reporting set for real-robot settings.

Developing intelligent agents that can effectively coordinate with diverse human partners is a fundamental goal of artificial general intelligence. Previous approaches typically generate a variety of partners to cover human policies, and then either train a single universal agent or maintain multiple best-response (BR) policies for different partners. However, the first direction struggles with the stochastic and multimodal nature of human behaviors, and the second relies on costly few-shot adaptations during policy deployment, which is unbearable in real-world applications such as healthcare and autonomous driving. Recognizing that human partners can easily articulate their preferences or behavioral styles through natural languages (NLs) and make conventions beforehand, we propose a framework for Human-AI Coordination via Policy Generation from Language-guided Diffusion (Haland). Haland first trains BR policies for various partners using reinforcement learning, and then compresses policy parameters into a single latent diffusion model, conditioned on task-relevant language derived from their behaviors. Finally, the alignment between task-relevant and NLs is achieved to facilitate efficient human-AI coordination. Empirical evaluations across diverse cooperative environments demonstrate that Haland generates agents with significantly enhanced zero-shot coordination performance, utilizing only NL instructions from various partners, and outperforms existing methods by approximately 89.64

Supervised Fine-Tuning (SFT) is a critical step for adapting Large Language Models (LLMs) to specialized domains, often serving as an initialization for subsequent reinforcement learning (RL). However, SFT can overfit a small set of expert data, harming generalization and eroding prior knowledge. This can limit downstream RL, which benefits from a strong, generalizable initialization for exploration. Here, we demonstrate that prior knowledge degradation primarily results from tokens in the expert data to which the base model assigns low probability. Specifically, these low-probability tokens represent a significant deviation from the model’s current prior knowledge. Due to the nature of the log-likelihood objective, they produce larger gradient magnitudes, which speed up adaptation to the new data but degrade generalization. In this paper, we study the token-wise clipping strategy, a commonly used trust-region method for bounding per-token updates. We find that it reshapes token-level learning priorities, promoting more progressive adaptation that fits the new data while preserving general abilities. Compared with standard SFT, clipping low-probability tokens reduces out-of-distribution forgetting by 11.54\% and improves final RL performance by 7.09\% across the agentic benchmarks. Moreover, latent-space analysis shows smaller representational drift under clipping, indicating that it provides a generalizable initialization.

Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings where tasks occur sequentially and the space of skills grows exponentially, existing approaches that rely on heuristically designed and fixed-sized skill libraries struggle to resolve the problem of distributional shift and interference, facing catastrophic forgetting and plasticity loss. To address this problem and endow agents with the ability to continually discover and reuse coordination skills in open-environment, we propose COMAD, a principled framework for ontinual ffline ulti-gent Skill iscovery via Skill Partition and Reuse. We first discover skills from mixed multi-agent behavior data with an auto-encoder to transform coordination knowledge into reusable coordination skills. Then we construct a skill-augmented policy learning objective with multi-head architectures, explicitly guiding the advantage function with reusable skills identified via a density-based reusability estimator. Theoretical analysis shows our method approximates the optimum of a continual skill discovery problem. Empirical results across diverse MARL benchmarks show that COMAD continually expands its skill library to mitigate interference, achieving superior forward and backward transfer for task streams compared to multiple baselines.

Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors inherent to behavioral cloning (BC), yet its adversarial optimization frequently leads to training instability. A class of non-adversarial Q-based imitation learning (IL) methods, exemplified by IQ-Learn, has emerged to address this instability and is widely believed to outperform BC by leveraging online environment interactions. In this paper, we revisit IQ-Learn and prove that it in fact reduces to BC: it admits an imitation gap lower bound with quadratic dependence on the horizon and therefore remains susceptible to compounding errors. Our theoretical analysis reveals why online interactions fail to help: IQ-Learn uniformly suppresses Q-values for all actions at states not covered by demonstrations, preventing generalization beyond demonstrations. To address this fundamental limitation, we introduce Dual Q-DM, a new Q-based IL method built on Bellman constraints. Crucially, Bellman constraints drive value flow: Q-values propagate from demonstrated to unvisited states through environment dynamics, enabling generalization beyond demonstrations. We prove that Dual Q-DM is equivalent to AIL and can recover expert actions at unvisited states, thereby mitigating compounding errors. To the best of our knowledge, Dual Q-DM is the first non-adversarial IL method that is theoretically guaranteed to eliminate compounding errors. Experimental results further corroborate our theoretical findings.

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents' current sub-trajectories, inform decision-making. During decentralized execution, we introduce a novel memory mechanism that effectively balances test-time online data with offline memory. Based on the constructed memory, we propose a hybrid utility score that incorporates both individual- and team-level returns, ensuring credit assignment across agents. Extensive experiments on cooperative MARL benchmarks, including Level-Based Foraging (LBF) and SMAC (v1/v2), show that MAICC enables faster adaptation to unseen tasks compared to existing methods.

Adversarial imitation learning (AIL) demonstrates superior expert sample efficiency compared to behavioral cloning (BC), yet requires substantial online environment interaction. While recent empirical work has explored initializing AIL algorithms with BC-pretrained policies to address this limitation, a rigorous theoretical understanding of pretraining's role in AIL remains lacking. This paper provides a systematic theoretical analysis and develops principled pretraining algorithms for accelerating AIL. We first analyze AIL with policy pretraining alone, identifying reward error as the dominant error source and thereby uncovering a critical yet previously unexplored gap: the omission of reward pretraining. Leveraging this insight, we introduce a principled policy-reward co-pretraining mechanism through reward-shaping analysis. Our analysis reveals a fundamental connection between expert policies and shaping rewards, naturally motivating CoPT-AIL, an approach that jointly pretrains both policies and rewards through a single BC procedure. We prove that CoPT-AIL achieves an improved imitation gap bound compared to standard AIL, establishing the first theoretical guarantee for pretraining benefits in AIL. Experimental results validate CoPT-AIL's superior performance over existing AIL methods.

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise positional information is often unavailable in real-world visual settings due to sensory and perceptual limitations. In this study, we propose a method that implicitly infers spatial distances through keypoints extracted from images. Building on this, we introduce Reward Learning with Anticipation Model (ReLAM), a novel framework that automatically generates dense, structured rewards from action-free video demonstrations. ReLAM first learns an anticipation model that serves as a planner and proposes intermediate keypoint-based subgoals on the optimal path to the final goal, creating a structured learning curriculum directly aligned with the task's geometric objectives. Based on the anticipated subgoals, a continuous reward signal is provided to train a low-level, goal-conditioned policy under the hierarchical reinforcement learning (HRL) framework with provable sub-optimality bound. Extensive experiments on complex, long-horizon manipulation tasks show that ReLAM significantly accelerates learning and achieves superior performance compared to SOTA methods.

Cooperative multi-agent reinforcement learning (MARL) aims to enable agents to achieve coordinated behaviors in complex environments. However, existing methods often struggle to strike a balance between rapid local adaptation and consistent long-term cooperation, resulting in poor coordination. To address this challenge, we propose Hierarchical Cognitive Learning (HCL), a framework inspired by hierarchical mechanisms of human decision-making. This framework models hierarchical cognitive processes by integrating short-term perceptual alignment for responsive coordination, long-term intent modeling for strategic abstraction, and cognitive policy generation that unifies both pathways to produce coherent joint behaviors. This design allows agents to dynamically balance immediate reactions and long-horizon planning under partial observability. We evaluate HCL on the Active Voltage Control (AVC) task, the StarCraft Multi-Agent Challenge (SMAC) benchmark, and the SMAC-Hard benchmark, covering both continuous and discrete action spaces. Experimental results demonstrate that HCL outperforms state-of-the-art methods, facilitating effective multi-agent coordination.

Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors in behavioral cloning (BC), but often exhibits training instability due to adversarial optimization. To avoid this issue, a class of non-adversarial Q-based imitation learning (IL) methods, represented by IQ-Learn, has emerged and is widely believed to outperform BC by leveraging online environment interactions. However, this paper revisits IQ-Learn and demonstrates that it provably reduces to BC and suffers from an imitation gap lower bound with quadratic dependence on horizon, therefore still suffering from compounding errors. Theoretical analysis reveals that, despite using online interactions, IQ-Learn uniformly suppresses the Q-values for all actions on states uncovered by demonstrations, thereby failing to generalize. To address this limitation, we introduce a primal-dual framework for distribution matching, yielding a new Q-based IL method, Dual Q-DM. The key mechanism in Dual Q-DM is incorporating Bellman constraints to propagate high Q-values from visited states to unvisited ones, thereby achieving generalization beyond demonstrations. We prove that Dual Q-DM is equivalent to AIL and can recover expert actions beyond demonstrations, thereby mitigating compounding errors. To the best of our knowledge, Dual Q-DM is the first non-adversarial IL method that is theoretically guaranteed to eliminate compounding errors. Experimental results further corroborate our theoretical results.