论文检索

Theory · Reinforcement Learning and Planning

Zixuan Ren, Jinliang Lu, Junhong Wu, Yang Zhao, Dai Dai, hua wu, Haifeng Wang, Chengqing Zong

Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehensive evaluations across five representative tasks, we find that RL significantly reduces task conflicts and results in less performance degradation after merging, making RL-trained models particularly well-suited for this process. To unearth the reasons behind the superior suitability of RL for model merging, we conduct extensive empirical experiments and theoretical analyses. Our findings highlight three key factors: (1) On-policy training data in RL control the gradient updates in a smaller magnitude, reducing the risk of overwriting existing knowledge for other tasks in the model. (2) The RL optimization objective, which favors "\textit{enough is as good as a feast}", progressively reduces the magnitude of parameter updates as the model converges, thereby alleviating inter-task conflicts. (3) Joint optimization of positive and negative examples in RL steers the model towards an unbiased task-specific parameter subspace, ensuring robust performance while further preventing parameter conflicts.

Theory · Reinforcement Learning and Planning

Ruibo Guo, Lei Liu, Rui Yang, Junjie Shen, Guoping Wu, Jie Wang, Bin Li

Offline-to-online reinforcement learning (O2O RL) aims to improve the performance of offline pretrained agents through online fine-tuning. Existing O2O RL methods have achieved advances in mitigating the overestimation of Q-value biases (i.e., biases of cumulative rewards), improving the performance. However, in this paper, we are the first to reveal that Q-value biases of these methods often follow a heavy-tailed distribution during online fine-tuning. Such biases induce high estimation variance and hinder performance improvement. To address this challenge, we propose a Laplace-based robust offline-to-online RL (LAROO) approach. LAROO introduces a parameterized Laplace-distributed noise and transfers the heavy-tailed nature of Q-value biases into this noise, alleviating heavy tailedness of biases for training stability and performance improvement. Specifically, (1) since Laplace distribution is well-suited for modeling heavy-tailed data, LAROO introduces a parameterized Laplace-distributed noise that can adaptively capture heavy tailedness of any data. (2) By combining estimated Q-values with the noise to approximate true Q-values, LAROO transfers the heavy-tailed nature of biases into the noise, reducing estimation variance. (3) LAROO employs conservative ensemble-based estimates to re-center Q-value biases, shifting their mean towards zero. Based on (2) and (3), LAROO promotes heavy-tailed Q-value biases into a standardized form, improving training stability and performance. Extensive experiments demonstrate that LAROO achieves significant performance improvement, outperforming several state-of-the-art O2O RL baselines.

Theory · Reinforcement Learning and Planning

Yudan Wang, Kaiyi Ji, Ming Shi, Shaofeng Zou

Consider episodic Markov decision processes (MDPs) with adversarially chosen transition kernels, where the transition kernel is adversarially chosen at each episode. Prior works have established regret upper bounds of $\widetilde{\mathcal{O}}(\sqrt{T} + C^P)$, where $T$ is the number of episodes and $C^P$ quantifies the degree of adversarial change in the transition dynamics. This regret bound may scale as large as $\mathcal{O}(T)$, leading to a linear regret. This raises a fundamental question: *Can sublinear regret be achieved under fully adversarial transition kernels?* We answer this question affirmatively. First, we show that the optimal policy for MDPs with adversarial transition kernels must be history-dependent. We then design an algorithm of Adversarial Dynamics Follow-the-Regularized-Leader (AD-FTRL), and prove that it achieves a sublinear regret of $\mathcal{O}(\sqrt{(|\mathcal{S}||\mathcal{A}|)^K T})$, where $K$ is the horizon length, $|\mathcal{S}|$ is the number of states, and $|\mathcal{A}|$ is the number of actions. Such a regret cannot be achieved by simply solving this problem as a contextual bandit. We further construct a hard MDP instance and prove a matching lower bound on the regret, which thereby demonstrates the **minimax optimality** of our algorithm.

Computer Vision · Vision Models & Multimodal

Xuyou Yang, Yucheng Zhao, Wenxuan Zhang, Immanuel Koh

Multi-modal Large Language Models (MLLMs) represent a significant advancement in artificial intelligence. Among the growing capabilities exhibited by MLLMs, abilities to understand and reason in real-world environments stand out as particularly vital as a fundamental prerequisite for a wide array of real-world applications. The current methods for evaluating MLLMs often fall short in their ability to comprehensively assess these crucial capabilities. However, being able to reason on complex environment-scale spaces, for example, room spaces, building spaces, and even urban spaces, and to predict the future and plan actions, is essential for humans and various autonomous agents to survive in the real physical world. To address these gaps, we propose a visual-question-answering benchmark, **SpaCE-Eval** (**Spa**tial Reasoning, **C**ommonsense Knowledge and **E**nvironment Interaction) in the real world, designed to evaluate some of MLLM’s most important reasoning abilities in real-world environments. As the name suggests, it challenges the models to reason on complex spatial scenarios, invoke commonsense knowledge of the physical world, and interact with the environment. The dataset consists of all new diagrams purposefully produced by humans, where diagram-question pairs are meticulously refined and selected through a rigorous pipeline. Additionally, with the benchmark, we evaluate a selection of leading MLLMs, both proprietary and open source. The results suggest that a significant enhancement of MLLMs in reasoning in the real physical world is necessary to realise more advanced general artificial intelligence.

Computer Vision · Vision Models & Multimodal

Huan-ang Gao, Zikang Zhang, Tianwei Luo, Kaisen Yang, Xinzhe Juan, Jiahao Qiu, Tianxing Chen, Bingxiang He, Hao Zhao, Hao Zhou 等

Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robust spatial mental model. We identify three core cognitive challenges hindering this transition: spatial reasoning, long-horizon state tracking via mental simulation, and active exploration under partial observation. To isolate and evaluate these faculties, we introduce \textbf{CubeBench}, a novel generative benchmark centered on the Rubik's Cube. CubeBench uses a three-tiered diagnostic framework that progressively assesses agent capabilities, from foundational state tracking with full symbolic information to active exploration with only partial visual data. Our experiments on leading LLMs reveal critical limitations, including a uniform 0.00\% pass rate on all long-horizon tasks, exposing a fundamental failure in long-term planning. We also propose a diagnostic framework to isolate these cognitive bottlenecks by providing external solver tools. By analyzing the failure modes, we provide key insights to guide the development of more physically-grounded intelligent agents.

Applications · Everything Else

Bo Jiang, Shaoyu Chen, Hao Gao, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang

Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. Existing learning-based planning methods follow a deterministic paradigm to directly regress the action, failing to cope with the uncertainty problem. In this work, we propose a probabilistic planning model for end-to-end autonomous driving, termed VADv2. We resort to a probabilistic field function to model the mapping from the action space to the probabilistic distribution. Since the planning action space is a high-dimensional continuous spatiotemporal space and hard to tackle, we first discretize the planning action space to a large planning vocabulary and then tokenize the planning vocabulary into planning tokens. Planning tokens interact with scene tokens and output the probabilistic distribution of action. Mass driving demonstrations are leveraged to supervise the distribution. VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming existing methods, and also leads the recent Bench2Drive benchmark. We further provide comprehensive evaluations on NAVSIM and a large-scale 3DGS-based benchmark, demonstrating its effectiveness in real-world applications. Code is available at https://github.com/hustvl/VAD.

Applications · Everything Else

Hao Tan, jun lan, Zichang Tan, Senyuan Shi, Ajian Liu, Chuanbiao Song, Huijia Zhu, Weiqiang Wang, Jun Wan, Zhen Lei

Deepfake detection remains a formidable challenge due to the evolving nature of fake content in real-world scenarios. However, existing benchmarks suffer from severe discrepancies from industrial practice, typically featuring homogeneous training sources and low-quality testing images, which hinder the practical usage of current detectors. To mitigate this gap, we introduce **HydraFake**, a dataset that contains diversified deepfake techniques and in-the-wild forgeries, along with rigorous training and evaluation protocol, covering unseen model architectures, emerging forgery techniques and novel data domains. Building on this resource, we propose **Veritas**, a multi-modal large language model (MLLM) based deepfake detector. Different from vanilla chain-of-thought (CoT), we introduce *pattern-aware reasoning* that involves critical patterns such as "planning" and "self-reflection" to emulate human forensic process. We further propose a two-stage training pipeline to seamlessly internalize such deepfake reasoning capacities into current MLLMs. Experiments on HydraFake dataset reveal that although previous detectors show great generalization on cross-model scenarios, they fall short on unseen forgeries and data domains. Our Veritas achieves significant gains across different out-of-domain (OOD) scenarios, and is capable of delivering transparent and faithful detection outputs.

Applications · Everything Else

Mingzhe Guo, Yixiang Yang, Chuanrong Han, Rufeng Zhang, Shirui Li, Ji Wan, Zhipeng Zhang

Effective environment modeling is the foundation for autonomous driving, underpinning tasks from perception to planning. However, current paradigms often inadequately consider the feedback of ego motion to the observation, which leads to an incomplete understanding of the driving process and consequently limits the planning capability. To address this issue, we introduce a novel ego-scene interactive modeling paradigm. Inspired by human recognition, the paradigm represents ego-scene interaction as the scene flow relative to the ego-vehicle. This conceptualization allows for modeling ego-motion feedback within a feature learning pattern, advantageously utilizing existing log-replay datasets rather than relying on scenario simulations. We specifically propose FlowAD, a general flow-based framework for autonomous driving. Within it, an ego-guided scene partition first constructs basic flow units to quantify scene flow. The ego-vehicle's forward direction and steering velocity directly shape the partition, which reflects ego motion. Then, based on flow units, spatial and temporal flow predictions are performed to model dynamics of scene flow, encompassing both spatial displacement and temporal variation. The final task-aware enhancement exploits learned spatio-temporal flow dynamics to benefit diverse tasks through object and region-level strategies. We also propose a novel Frames before Correct Planning (FCP) metric to assess the scene understanding capability. Experiments in both open and closed-loop evaluations demonstrate FlowAD's generality and effectiveness across perception, end-to-end planning, and VLM analysis. Notably, FlowAD reduces 19\% collision rate over SparseDrive with FCP improvements of 1.39 frames (60\%) on nuScenes, and achieves an impressive driving score of 51.77 on Bench2Drive, proving the superiority. Code, model, and configurations will be released here.

Xiaotian Liu, Armin Toroghi, Jiazhou Liang, David Courtis, Ruiwen Li, Ali Pesaranghader, Jaehong Kim, Tanmana Sadhu, Hyejeong Jeon, Scott Sanner

Planning in open-world environments, where agents must act with partially observed states and incomplete knowledge, is a central challenge in embodied AI. Open-world planning involves not only sequencing actions but also determining what information the agent needs to sense to enable those actions. Existing approaches using Large Language Models (LLM) and Vision-Language Models (VLM) cannot reliably plan over long horizons and complex goals, where they often hallucinate and fail to reason causally over agent-environment interactions. Alternatively, classical PDDL planners offer correct and principled reasoning, but fail in open-world settings: they presuppose complete models and depend on exhaustive grounding over all objects, states, and actions; they cannot address misalignment between goal specifications (e.g., “heat the bread”) and action specifications (e.g., “toast the bread”); and they do not generalize across modalities (e.g., text, vision). To address these core challenges: (i) we extend symbolic PDDL into a flexible natural language representation that we term NL-PDDL, improving accessibility for non-expert users as well as generalization over modalities; (ii) we generalize regression-style planning to NL-PDDL with commonsense entailment reasoning to determine what needs to be observed for goal achievement in partially-observed environments with potential goal–action specification misalignment; and (iii) we leverage the lifted specification of NL-PDDL to facilitate open-world planning that avoids exhaustive grounding and yields a time and space complexity independent of the number of ground objects, states, and actions. Our experiments in three diverse domains — classical Blocksworld and the embodied ALFWorld environment with both textual and visual states — show that NL-PDDL substantially outperforms existing baselines, is more robust to longer horizons and more complex goals, and generalizes across modalities.

Reinforcement Learning · Batch/Offline

Huazhong Wang, Wenzhuo Zhou

We study reinforcement learning (RL) with trajectory preferences, where the RL agent does not receive explicit rewards at each step but instead receives human-AI preferences over pairs of trajectories. Despite growing interest in preference-based reinforcement learning (PbRL), contemporary works cannot robustly learn policies in offline settings with poor data coverage and often lack algorithmic tractability. We propose a novel **M**odel-based **C**onservative **P**lanning (MCP) algorithm for offline PbRL, which leverages a general function class and uses a tractable conservative learning framework to improve the policy upon an arbitrary reference policy. We prove that, MCP can compete with the best policy within data coverage when the reference policy is supported by the data. To the best of our knowledge, MCP is the first provably sample-efficient and computationally tractable offline PbRL algorithm under partial data coverage, without requiring known transition dynamics. We further demonstrate that, with certain structural properties in PbRL dynamics, our algorithm can effectively exploit these structures to relax the partial data coverage requirement and improve regret guarantees. We evaluate MCP on a comprehensive suite of human-in-the-loop benchmarks in Meta-World. Experimental results show that our algorithm achieves competitive performance compared to state-of-the-art offline PbRL algorithms. Our code is provided at https://github.com/Rshias/MCP.

Applications · Neuroscience, Cognitive Science

Xiao-Xiong Lin, Yuk-Hoi Yiu, Christian Leibold

Sequential firing of hippocampal place cells is often attributed to sequential sensory drive along a trajectory, and has also been attributed to planning and other cognitive functions. Here, we propose a mechanistic and parsimonious interpretation to complement these ideas: hippocampal sequences arise from intrinsic recurrent circuitry that propagates transient input over long horizons, acting as a temporal memory buffer that is especially useful when reliable sensory evidence is sparse. We implement this idea with a minimal sequence generator inspired by neurobiology and pair it with an actor–critic learner for egocentric visual navigation. Our agent reliably solves a continuous maze without explicit geometric cues, with performance depending on the length of the recurrent sequence. Crucially, the model outperforms LSTM cores under sparse input conditions (16 channels, $\sim2.5\%$ activity), but not under dense input, revealing a strong interaction between representational sparsity and memory architecture. Through learning, units develop localized place fields, distance-dependent spatial kernels, and task-dependent remapping, while inputs to the sequence generator orthogonalize and spatial information increases across layers. These phenomena align with neurobiological data and are causal to performance. Together, our results show that sparse input synergizes with sequence-generating dynamics, providing both a mechanistic account of place cell sequences in the mammalian hippocampus and a simple inductive bias for reinforcement learning based on sparse egocentric inputs in navigation tasks.

Applications · Neuroscience, Cognitive Science

Shaan Shah, Meenakshi Khosla

Standard representational similarity methods align each layer of a network to its best match in another independently, producing asymmetric results, lacking a global alignment score, and struggling with networks of different depths. These limitations arise from ignoring global activation structure and restricting mappings to rigid one-to-one layer correspondences. We propose Multi-Level Optimal Transport (MOT), a unified framework that jointly infers soft, globally consistent layer-to-layer couplings and neuron-level transport plans. MOT allows source neurons to distribute mass across multiple target layers while minimizing total transport cost under marginal constraints. This yields both a single alignment score for the entire network comparison and a soft transport plan that naturally handles depth mismatches through mass distribution. We evaluate MOT on vision models, large language models, and human visual cortex recordings. Across all domains, MOT matches or surpasses standard pairwise matching in alignment quality. Moreover, it reveals smooth, fine-grained hierarchical correspondences: early layers map to early layers, deeper layers maintain relative positions, and depth mismatches are resolved by distributing representations across multiple layers. These structured patterns emerge naturally from global optimization without being imposed, yet are absent in greedy layer-wise methods. MOT thus enables richer, more interpretable comparisons between representations, particularly when networks differ in architecture or depth. We further extend our method to a three-level MOT framework, providing a proof-of-concept alignment of two networks across their training trajectories and demonstrating that MOT uncovers checkpoint-wise correspondences missed by greedy layer-wise matching.

Kai Yang, Tianlin Zhang, Zhengbo Wang, Zedong Chu, Xiaolong Wu, Yang Cai, Mu Xu

Generalizing local navigation policies across diverse robot morphologies is a critical challenge. Progress is often hindered by the need for costly and embodiment-specific data, the tight coupling of planning and control, and the "disastrous averaging" problem where deterministic models fail to capture multi-modal decisions (e.g., turning left or right). We introduce CE-Nav, a novel two-stage (IL-then-RL) framework that systematically decouples universal geometric reasoning from embodiment-specific dynamic adaptation. First, we train an embodiment-agnostic General Expert offline using imitation learning. This expert, a conditional normalizing flow model named VelFlow, learns the full distribution of kinematically-sound actions from a large-scale dataset generated by a classical planner, completely avoiding real robot data and resolving the multi-modality issue. Second, for a new robot, we freeze the expert and use it as a guiding prior to train a lightweight, Dynamics-Aware Refiner via online reinforcement learning. This refiner rapidly learns to compensate for the target robot's specific dynamics and controller imperfections with minimal environmental interaction. Extensive experiments on quadrupeds, bipeds, and quadrotors show that CE-Nav achieves state-of-the-art performance while drastically reducing adaptation cost. Successful real-world deployments further validate our approach as an efficient and scalable solution for building generalizable navigation systems.

Applications · Language, Speech and Dialog

Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen, Peiwen Sun, Rongjie Huang, Xiangang Li, Jieping Ye, Wei Xue

Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and lack human preference alignment. We introduce **PrismAudio**, the first framework to integrate Reinforcement Learning into V2A generation with specialized Chain-of-Thought (CoT) planning. Our approach decomposes monolithic reasoning into four specialized CoT modules (Semantic, Temporal, Aesthetic, and Spatial CoT), each paired with targeted reward functions. This CoT-reward correspondence enables **multidimensional RL optimization** that guides the model to jointly generate better reasoning across all perspectives, solving the objective entanglement problem while preserving interpretability. To make this optimization computationally practical, we propose **Fast-GRPO**, which employs hybrid ODE-SDE sampling that dramatically reduces the training overhead compared to existing GRPO implementations. We also introduce **AudioCanvas**, a rigorous benchmark that is more distributionally balanced and covers more realistically diverse and challenging scenarios than existing datasets, with 300 single-event classes and 501 multi-event samples. Experimental results demonstrate that PrismAudio achieves state-of-the-art performance across all four perceptual dimensions on both the in-domain VGGSound test set and out-of-domain AudioCanvas benchmark. The project page is available at~\url{https://PrismAudio.github.io}.

Applications · Language, Speech and Dialog

Yuxin Shi, Han Fu, Zhuo Li, Chenghao Liu, Xiaoxue Ren, Jianling Sun

Incorporating knowledge graphs (KGs) into large language model (LLM) reasoning has shown promise in alleviating hallucinations and factual errors. Although existing paradigms of KG-augmented LLMs have achieved encouraging results, they still exhibit notable limitations when handling multi-hop reasoning and complex logical queries: (1) search space truncation bias: current methods generate linear entity-relation reasoning paths, which can prune correct candidates prematurely during iterative exploration; and (2) entity error amplification: existing methods typically follow the retrieve-and-answer paradigm which causes LLMs to over-rely on retrieved evidence, exacerbating the impact of incorrect entities during reasoning. To alleviate the existing challenges, we propose Plan-Answer-Refine-on-Graph (PARoG), a novel framework for LLM reasoning on knowledge graphs. First, PARoG leverages SPARQL queries from KG data as references, decomposing them into structured step-by-step plans. We further train LLMs to construct such structured plans, which improves the logical consistency of reasoning, ensures uniform step granularity, and facilitates effective execution on the graph. Second, during reasoning over KGs, PARoG adopts a plan-answer-refine paradigm: the model first attempts to answer each sub-query independently, and then refines its prediction by integrating evidence retrieved from the KG. This process mitigates knowledge conflicts between LLM and KG, substantially reducing hallucinations. Experimental results on multiple KG reasoning benchmarks demonstrate that PARoG significantly outperforms state-of-the-art approaches, achieving especially superior accuracy on multi-hop and logically complex queries.

Theory · Reinforcement Learning and Planning

Priyank Agrawal, Shipra Agrawal, Azmat Azati

Bayesian posterior sampling techniques have demonstrated superior empirical performance in many exploration-exploitation settings. However, their theoretical analysis remains a challenge, especially in complex settings like reinforcement learning. In this paper, we introduce Q-Learning with Posterior Sampling (PSQL), a simple Q-learning-based algorithm that uses Gaussian posteriors on Q-values for exploration, akin to the popular Thompson Sampling algorithm in the multi-armed bandit setting. We show that in the tabular episodic MDP setting, PSQL achieves a regret bound of $\tilde O(H^2\sqrt{SAT})$, closely matching the known lower bound of $\Omega(H\sqrt{SAT})$. Here, S, A denote the number of states and actions in the underlying Markov Decision Process (MDP), and $T=KH$ with $K$ being the number of episodes and $H$ being the planning horizon. Our work provides several new technical insights into the core challenges in combining posterior sampling with dynamic programming and TD-learning-based RL algorithms, along with novel ideas for resolving those difficulties. We hope this will form a starting point for analyzing this efficient and important algorithmic technique in even more complex RL settings.

General Machine Learning · Probabilistic Methods

Zihang Zeng, Jiaquan Zhang, Pengze Li, Yuan Qi, Xi Chen

Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and evaluation in domains with ill-defined success metrics. We present a Bayesian adversarial multi-agent framework specifically designed for AI for Science (AI4S) tasks in the form of a Low-code Platform (LCP). Three LLM-based agents are coordinated under the Bayesian framework: a Task Manager that structures user inputs into actionable plans and adaptive test cases, a Code Generator that produces candidate solutions, and an Evaluator providing comprehensive feedback. The framework employs an adversarial loop where the Task Manager iteratively refines test cases to challenge the Code Generator, while prompt distributions are dynamically updated using Bayesian principles by integrating code quality metrics: functional correctness, structural alignment, and static analysis. This co-optimization of tests and code reduces dependence on LLM reliability and addresses evaluation uncertainty inherent to scientific tasks. LCP also streamlines human-AI collaboration by translating non-expert prompts into domain-specific requirements, bypassing the need for manual prompt engineering by practitioners without coding backgrounds. Benchmark evaluations demonstrate LCP’s effectiveness in generating robust code while minimizing error propagation. The proposed platform is also tested on an Earth Science cross-disciplinary task and demonstrates strong reliability, outperforming competing models.

Theory · Game Theory

Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla, Xinghua Lou, Carter Wendelken, Zun Li, Antoine Dedieu, Marc Lanctot, Atil Iscen, John Schultz 等

Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach---involving prompting for direct move generation---has significant drawbacks. It relies on the model's implicit fragile pattern-matching capabilities, leading to frequent illegal moves and strategically shallow play. Here we introduce an alternative approach: We use the LLM to translate natural language rules and game trajectories into a formal, executable world model represented as Python code. This generated model---comprising functions for state transition, legal move enumeration, and termination checks---serves as a verifiable simulation engine for high-performance planning algorithms like Monte Carlo tree search (MCTS). In addition, we prompt the LLM to generate heuristic value functions (to make MCTS more efficient), and inference functions (to estimate hidden states in imperfect information games). Our method offers three distinct advantages compared to directly using the LLM as a policy: (1) Verifiability: The generated CWM serves as a formal specification of the game's rules, allowing planners to algorithmically enumerate valid actions and avoid illegal moves, contingent on the correctness of the synthesized model; (2) Strategic Depth: We combine LLM semantic understanding with the deep search power of classical planners; and (3) Generalization: We direct the LLM to focus on the meta-task of data-to-code translation, enabling it to adapt to new games more easily. We evaluate our agent on 10 different games, of which 4 are novel and created for this paper. 5 of the games are fully observed (perfect information), and 5 are partially observed (imperfect information). We find that our method outperforms or matches Gemini 2.5 Pro in 9 out of the 10 considered games.

Applications · Robotics

Yuecheng Liu, DaFeng Chi, Shiguang Wu, Zhanguang Zhang, Yuzheng Zhuang, Bowen Yang, He Zhu, Lingfeng Zhang, Pengwei Xie, David Gamaliel Arcos Bravo 等

Recent advances in multimodal large language models (MLLMs) have opened new opportunities for embodied intelligence, enabling multimodal understanding, reasoning, and interaction, as well as continuous spatial decision-making. Nevertheless, current MLLM-based embodied systems face two critical limitations. First, **Geometric Adaptability Gap:** models trained solely on 2D inputs or with hard-coded 3D geometry injection suffer from either insufficient spatial information or restricted 2D generalization, leading to poor adaptability across tasks with diverse spatial demands. Second, **Embodiment Constraint Gap**: prior work often neglects the physical constraints of real robots, resulting in task plans that are theoretically valid but practically infeasible.To address these gaps, we introduce **OmniEVA** -- an embodied versatile planner that enables advanced embodied reasoning and task planning through two pivotal innovations: (1) a **Task-Adaptive 3D Grounding** mechanism, which uses a gated router to dynamically inject 3D features based on task context, enabling selective geometric reasoning. (2) an **Embodiment-Aware Reasoning** framework that incorporates task goals and physical constraints into the reasoning loop, ensuring executable plans. Extensive experiments show that OmniEVA achieves state-of-the-art performance on 7 of 8 embodied reasoning benchmarks and excels in downstream tasks such as object navigation and mobile manipulation. Evaluations on proposed primitive and composite benchmarks confirm its robust and versatile planning capabilities.

Reinforcement Learning · Planning

Zikang Tian, Shaohui Peng, Di Huang, Jiaming Guo, Ruizhi Chen, Rui Zhang, Xishan Zhang, Yuxuan Guo, Zidong Du, Qi Guo 等

Large Language Models (LLMs) have been widely adopted as task planners for AI agents in sequential decision-making problems, leveraging their extensive world knowledge. However, the gap between their general knowledge and environment-specific requirements often leads to inaccurate plans. To address this, existing approaches rely on frequent LLM queries to iteratively refine plans based on immediate environmental feedback, which incurs substantial query costs. However, this refinement is typically guided by short-term environmental feedback, limiting LLMs from developing plans aligned with long-term rewards. We propose **Co**de Driven **P**lanning w**i**th Domain-Adaptive Sele**C**tor (CoPiC). Instead of relying on frequent queries, CoPiC employs LLMs to generate a diverse set of high-level planning programs, which iteratively produce and refine candidate plans. A trained domain-adaptive selector then evaluates these candidates and selects the one most aligned with long-term rewards for execution. Using high-level planning programs as planner and domain-adaptive selector as estimator, CoPiC improves planning while significantly reducing query costs. Results in ALFWorld, NetHack, and StarCraft II Unit Building show that CoPiC outperforms advanced LLM-based baselines, achieving an average (1) 19.14\% improvement in success rate and (2) 79.39\% reduction in token costs.