论文检索

Theory · Reinforcement Learning and Planning

Egor Cherepanov, Daniil Zelezetsky, Aleksandr Panov, Aleksey Kovalev

Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis. We introduce KAGE-Env, a JAX-native 2D platformer that factorizes the observation process into independently controllable visual axes while keeping the underlying control problem fixed. By construction, varying a visual axis affects performance only through the induced state-conditional action distribution of a pixel policy, providing a clean abstraction for visual generalization. Building on this environment, we define KAGE-Bench, a benchmark of six known-axis suites comprising 34 train-evaluation configuration pairs that isolate individual visual shifts. Using a standard PPO-CNN baseline, we observe strong axis-dependent failures, with background and photometric shifts often collapsing success, while agent-appearance shifts are comparatively benign. Several shifts preserve forward motion while breaking task completion, showing that return alone can obscure generalization failures. Finally, the fully vectorized JAX implementation enables up to 33M environment steps per second on a single GPU, enabling fast and reproducible sweeps over visual factors.

Theory · Optimization

Owen Shen, Haoran Xu, Yinyu Ye, Peter Glynn, Patrick Jaillet

We study online configuration selection with admission control problem, which arises in LLM serving, GPU scheduling, and revenue management. In a planning horizon with $T$ periods, we consider a two-layer framework for the decisions made within each time period. In the first layer, the decision maker selects one of the $K$ configurations (ex. quantization, parallelism, fare class) which induces distribution over the reward-resource pair of the incoming request. In the second layer, the decision maker observes the request and then decides whether to accept it or not. Benchmarking this framework requires care. We introduce a \textbf{switching-aware fluid oracle} that accounts for the value of mixing configurations over time, provably upper-bounding any online policy. We derive a min-max formulation for evaluating the benchmark, and we characterize saddle points of the max-min problem via primal-dual optimality conditions linking equilibrium, feasibility, and complementarity. This guides the design of \textbf{SP-UCB--OLP} algorithm, which solves an optimistic saddle point problem and achieves $\tilde{O}(\sqrt{KT})$ regret.

Deep Learning · Large Language Models

Jingzhe Ding, Shengda Long, Changxin Pu, Ge Zhang, zhou huan, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, FEI HU 等

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks primarily evaluate short-horizon behaviors such as localized code generation, scaffolded completion, or repository repair, leaving it unclear whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we introduce NL2Repo-Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation from scratch: given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, and produce a fully installable Python library. Experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved, with even the strongest agents achieving merely 40\% average test pass rates and rarely completing an entire repository correctly. Further analysis identifies systematic long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. These results position NL2Repo-Bench as a rigorous, execution-based testbed for evaluating sustained agentic competence and highlight long-horizon reasoning as a key bottleneck for autonomous coding agents. Our data and code are available at https://anonymous.4open.science/r/nl2repobench-foricml-F4ED/.

Deep Learning · Other Representation Learning

Shicheng Yin, Kaixuan Yin, Weixing Chen, Yang Liu, Guanbin Li, Liang Lin

World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformer-based models significantly hinders real-time deployment. To address this efficiency-performance bottleneck, we introduce DDP-WM, a novel world model centered on the principle of Disentangled Dynamics Prediction (DDP). We hypothesize that latent state evolution in observed scenes is heterogeneous and can be decomposed into sparse primary dynamics driven by physical interactions and secondary context-driven background updates. DDP-WM realizes this decomposition through an architecture that integrates efficient historical processing with dynamic localization to isolate primary dynamics. By employing a cross-attention mechanism for background updates, the framework optimizes resource allocation and provides a smooth optimization landscape for planners. Extensive experiments demonstrate that DDP-WM achieves superior efficiency and performance across diverse tasks, including navigation, precise tabletop manipulation, and complex deformable or multi-body interactions. Specifically, on the challenging Push-T task, DDP-WM achieves an approximately 9 times inference speedup and improves the MPC success rate from 90% to 98% compared to state-of-the-art dense models.

Deep Learning · Large Language Models

Mathieu Blondel, Michael Sander, Germain Vivier-Ardisson, Tianlin Liu, Vincent Roulet

Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent another class of models, which have historically been less prevalent in LLM development, yet naturally characterize the optimal policy in post-training alignment. In this paper, we present a unified view of these two model classes. Taking the chain rule of probability as a starting point, we establish an explicit bijection between ARMs and EBMs in function space, which we show to correspond to a special case of the soft Bellman equation in maximum entropy reinforcement learning. Building upon this bijection, we derive the equivalence between supervised learning of ARMs and EBMs. Furthermore, we analyze the distillation of EBMs into ARMs by providing theoretical error bounds. Our results provide insights into the ability of ARMs to plan ahead, despite being based on the next-token prediction paradigm.

Applications · Robotics

Zhiyi Li, Peilin Wu, Xiaoshen Han, Ruojin Cai, Yilun Du

Learned world models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making. However, prevailing approaches often operate on 2D video sequences, inherently lacking the 3D geometric understanding necessary for precise spatial reasoning and physical consistency. We introduce a **Structured 4D Latent World Model**, which predicts the evolution of a scene’s 3D structure in a structured latent space conditioned on observations and textual instructions. Our representation encodes the scene holistically and can be decoded into diverse 3D formats, enabling a more complete and physically consistent scene understanding. This structured 4D latent world model serves as a planner, generating future scenes that are translated into executable actions by a goal-conditioned inverse dynamics module. Experiments demonstrate that our model generates futures with superior visual quality, physical consistency, and multi-view coherence compared to state-of-the-art video-based planners. Consequently, our full planning pipeline achieves superior performance on complex manipulation tasks, exhibits robust generalization to novel visual conditions, and proves effective on real-world robotic platforms. Our website is available at https://icml2026-18617.github.io/.

Applications · Everything Else

Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li

Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7\%, 38.2\%, and 15.9\% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7\%, 9.5\%, and 2.8\% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach.

Deep Learning · Large Language Models

Maggie Ziyu Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue

Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to transfer their gains to other domains. To rigorously study this phenomenon, we conduct controlled experiments using math-only data with two widely-used methods: Reinforcement Learning (RL) and Supervised Finetuning (SFT) with detailed ablations. On top of the observation that RL-tuned models transfer better than SFT-tuned model, we identify on-policy fine-tuning as the key mechanism underlying cross-domain transfer, regardless of whether the training signal comes from RL or supervised learning. Latent-space representation and token-space distribution shift analyses reveal that off-policy SFT induces substantial representation and output drift, while on-policy RL preserves general-domain structure. Our results suggest a need to rethink the post-training recipes, particularly the reliance on off-policy SFT-distilled data to advance reasoning models.

Reinforcement Learning · Batch/Offline

Evgenii Opryshko, Junwei Quan, Claas Voelcker, Yilun Du, Igor Gilitschenski

Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is typically assumed that effective long-term planning is infeasible without specialized training. In contrast, our work demonstrates that existing GCRL policies can complete long-horizon tasks when combined with a lightweight, training-free planning wrapper. We find that standard goal-conditioned value functions encode locally consistent geometric structure sufficient for planning. Our approach, Test-Time Graph Search (TTGS), constructs a graph over the offline dataset and employs an adaptive subgoal selection strategy. To address unreliable value estimates during shortest-path search, we propose a novel mechanism that softly penalizes long-distance transitions. Our method incurs negligible computational overhead and requires no additional supervision or parameter updates. On the OGBench benchmark, TTGS unlocks latent capabilities in diverse base learners, boosting success rates on challenging locomotion tasks from near-zero to over 90\%, often matching or outperforming methods that require complex auxiliary training.

Deep Learning · Graph Neural Networks

Kunal Mukherjee, Zulfikar Alom, Tran Gia Bao Ngo, Cuneyt Akcora, Murat Kantarcioglu

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice, attackers continuously adapt their strategies as well as must operate under domain-specific and temporal constraints, which can fundamentally limit the applicability of existing attack methods. As a result, there is a critical need for robust GNN-based bot detection methods under realistic, constraint-aware attack scenarios. To address this gap, we introduce BOCLOAK to systematically evaluate the robustness of GNN-based social bot detection via both edge editing and node injection adversarial attacks under realistic constraints. BOCLOAK constructs a probability measure over spatio-temporal neighbor features and learns an optimal transport geometry that separates human and bot behaviors. It then decodes transport plans into sparse, plausible edge edits that evade detection while obeying real-world constraints. We evaluate BOCLOAK across three social bot datasets, five state-of-the-art bot detectors, three adversarial defenses, and compare it against four leading graph adversarial attack baselines. BOCLOAK achieves up to 80.13% higher attack success rates while using 99.80% less GPU memory under realistic real-world constraints. Most importantly, BOCLOAK shows that optimal transport provides a lightweight, principled framework for bridging adversarial attacks and real-world bot detection

Applications · Computer Vision

Mingde Yao, Zhiyuan You, King-Man Tam, Menglu Wang, Tianfan Xue

With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing highly depends on carefully designed instructions, placing the burden of task decomposition and sequencing entirely on the user. To achieve autonomous image editing, we present PhotoAgent, a system that advances image editing through explicit aesthetic planning. Specifically, PhotoAgent formulates autonomous image editing as a long-horizon decision-making problem. It reasons over user aesthetic intent, plans multi-step editing actions via tree search, and iteratively refines results through closed-loop execution with memory and visual feedback, without requiring step-by-step user prompts. To support reliable evaluation in real-world scenarios, we introduce UGC-Edit, an aesthetic evaluation benchmark consisting of 7,000 photos and a learned aesthetic reward model. We also construct a test set containing 1,017 photos to systematically assess autonomous photo editing performance. Extensive experiments demonstrate that PhotoAgent significantly outperforms existing methods in both instruction faithfulness and visual quality across a diverse range of editing scenarios.

Deep Learning · Large Language Models

Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou

This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs) is shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT; whereas CoT remains critical for tasks requiring multi-step reasoning. To deepen the understanding between LLM's internal states and its verbalized reasoning trajectories, we investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains. Our empirical results indicate that LLMs exhibit a *myopic* horizon, primarily conducting incremental transitions without precise global planning. Leveraging this characteristic, we propose a hypothesis on enhancing uncertainty estimation of CoT, which we validate that a small subset of CoT positions can effectively represent the uncertainty of the entire path. We further underscore the significance of exploiting CoT dynamics, and demonstrate that automatic recognition of CoT bypass can be achieved without performance degradation.

Applications · Time Series

Tianmi Ma, Wenxin Huang, Jiawei Du, Lin Li, Xian Zhong, Joey Tianyi Zhou

Large Language Models (LLMs) exhibit strong capabilities in high-level semantic understanding and strategic planning, yet they suffer from persistent quantitative failure modes, such as imprecise computation and the illusion of quantitative coherence, which limit their reliability in high-stakes decision-making. To address these limitations, we decouple reasoning from computation by assigning LLMs to planning, analysis, and result interpretation, while delegating numerical computation and statistical inference to specialized external tools. These tools are not hard-coded; instead, they are created in a constrained and structured manner during planning as explicit intermediate reasoning artifacts, enabling adaptive and scenario-dependent quantitative reasoning. LLMs iteratively analyze tool outputs under diverse market conditions and leverage performance-based feedback to refine subsequent tool selection and construction, forming a bounded self-evolving loop. We instantiate this process through self-play in a controllable digital twin market, DecoupledMarket, where LLM agents continuously test, compare, and adapt their strategies. By coupling high-level planning with robust quantitative execution, the proposed framework improves the quantitative reliability of LLM-driven decision-making. Code will be released soon.

Reinforcement Learning · Deep RL

Shiyi Wang, Yuyuan Chen, Peter Potaptchik, Jaeyeon Kim, Michael Albergo

Masked diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. While reinforcement learning (RL) algorithms have been adapted to be compatible with dLLMs for fine-tuning them, their reliance on the computation of the marginal likelihood to evaluate policy objectives is intractable. To overcome this, we exploit a dynamical relation between the unmasking posterior of the base model and that which targets the reward-tilted distribution to derive Discrete Tilt Matching (DTM), an algorithm that avoids intractable likelihood evaluation entirely. DTM can be phrased as a cross-entropy loss that only requires forward evaluation of rewards and whose variance can be adaptively controlled, improving training stability. We motivate DTM on maze planning tasks, and show that fine-tuning LLaDA-8B-Instruct with DTM achieves higher accuracy at lower compute costs than prior RL-based fine-tuning methods across the Sudoku, Countdown, and MATH500 benchmarks.

Optimization · Discrete and Combinatorial Optimization

Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic heuristic generation, redundant evaluations, and limited reasoning about how new heuristics should be derived. We propose a novel multi-agent reasoning framework, referred to as Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (PathWise), which formulates heuristic generation as a sequential decision process over an entailment graph serving as a compact, stateful memory of the search trajectory. This approach allows the system to carry forward past decisions and reuse or avoid derivation information across generations. A policy agent plans evolutionary actions, a world model agent generates heuristic rollouts conditioned on those actions, and critic agents provide routed reflections summarizing lessons from prior steps, shifting LLM-based AHD from trial-and-error evolution toward state-aware planning through reasoning. Experiments across diverse COPs show that PathWise converges faster to better heuristics, generalizes across different LLM backbones, and scales to larger problem sizes.

Deep Learning · Large Language Models

YaoQi Fan, Zhe Chen, Wei Zhu, Kangxin Yin, Yangzhou Liu, Yue Cao, Zhi Zhu, Tong Lu

Vision–Language Models (VLMs) are increasingly deployed with web search tools, yet we still lack benchmarks that isolate a critical capability for real-world use: deciding when to search and how to steer search from ambiguous visual evidence, especially when multiple images provide overlapping or conflicting cues. We introduce NAVIGATE, a novel benchmark centered on images as primary evidence for open-web search planning and multi-step reasoning. It contains 500 questions across 20 domains and spans three difficulty tiers, from single-image, self-contained problems to multi-image joint search and multi-domain composition. Unlike prior benchmarks that specify explicit search targets, NAVIGATE evaluates search decision-making: models must infer whether external search is necessary and iteratively refine search directions based on holistic reasoning over visual cues. Across a broad set of VLMs and search-enabled systems, performance remains low, Gemini-3-Pro-Preview-Search reaches only 36.4% accuracy, highlighting persistent failures in cross-image grounding, search triggering, and search strategy coordination. We will release NAVIGATE publicly.

Deep Learning · Large Language Models

Omer Luxembourg, Haim Permuter, Eliya Nachmani

Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions sequence positions into non-adjacent dilated groups and unmasked them in parallel so as to minimize an upper bound on joint entropy gain at each denoising step. By explicitly trading off the number of network calls against generation quality, DUS recovers most of the performance lost under traditional parallel unmasking strategies. Across math (GSM8K, MATH500), code (HumanEval, MBPP), general‐knowledge (BBH, MMLU-Pro), and instruction following (IFEval) benchmarks, DUS outperforms confidence‐based planners, without modifying the underlying denoiser, and reveals the true speed-quality frontier of MDLMs.

Theory · Reinforcement Learning and Planning

Ryan Anderson, Guido Montufar

We study the geometry of feasible value functions in infinite-horizon partially observable Markov decision processes (POMDPs) under memoryless stochastic policies. Our main contribution is a characterization of the feasible set of value functions as a semi-algebraic set, defined by explicit polynomial inequalities determined by the transition dynamics, observation kernel, and reward structure of the POMDP. This result extends prior work for fully observable Markov decision processes, where the feasible set is known to be a polytope, to the substantially more intricate partially observable setting. In contrast to the polyhedral structure arising in MDPs, partial observability induces fundamentally nonlinear constraints, leading to a richer and more complex geometric structure. Our geometric characterization provides new insight into the landscape of policy optimization in both MDPs and POMDPs, and reveals qualitative phenomena unique to partial observability, including the emergence of isolated local maximizers of the long-term reward and their dependence on the initial state distribution.

Theory · Reinforcement Learning and Planning

Abdullah Akgül, Gulcin Baykal, Manuel Haussmann, Mustafa Mert Çelikok, Melih Kandemir

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning framework addresses only the latter, it tends to deliver sample-inefficient solutions. Active inference is the state-of-the-art process theory that explains how biological brains handle this dual problem. However, its applications to artificial intelligence have thus far been limited to extensions of existing model-based approaches. We present a formal abstraction of reinforcement learning algorithms that spans model-based, distributional, and model-free approaches. This abstraction seamlessly integrates active inference into the distributional reinforcement learning framework, making its performance advantages accessible without transition dynamics modeling.

Theory · Reinforcement Learning and Planning

Yifan Jiang, Jiasheng Pan, Mengtian Li, Li Jin

We study decentralized multi-agent reinforcement learning (MARL) for networked service systems with affinity in the presence of Byzantine nodes. The way that a server processes a job depends on an affinity state that captures the correlation between the job and the server. Each node learns a local control policy via an actor-critic algorithm with linear function approximation over inherently unbounded space of traffic states, while exchanging parameter information with neighbors through a communication graph. A set of Byzantine agents can exploit the unbounded state space and the resulting stochastic variance to compromise the consensus mechanism, destabilizing both learning and queuing processes. To address this vulnerability, we propose a resilient consensus-based MARL algorithm with momentum-based smoothing, which mitigates adversarial parameter manipulation and guarantees traffic stability under mild assumptions. We prove that the cooperative agents’ policies converge almost surely to a bounded neighborhood of a stationary solution of the global objective. We demonstrate the effectiveness and generality of the proposed framework in several representative service systems, including semantic routing for large language model serving, distributed polling in cloud computing, and smart manufacturing logistics.