NeurIPS 2026 Papers

Open-world task planning requires not only generating feasible plans but also acquiring the knowledge needed to execute them. Existing task planners for egocentric agents either attempt to exhaustively gather information from the environment or generate plans under prior assumptions of the world and replan as new observations arrive. Both strategies are impractical in complex environments and can potentially expose agents to undesirable or unsafe situations. To enable effective planning in open-world settings, we propose Plan2Sense, a framework that grounds planning in the agent’s epistemic state to determine what information is required for plan feasibility and how to acquire it. We formalize decision-making as a three-valued first-order Knowledge-State Markov Decision Process (KS-MDP) and develop a knowledge state goal regression algorithm KSR to construct sensing-aware conditional plans in the open-world setting. Our formulation supports sensing actions for both predicate disambiguation and knowledge acquisition via object binding without assuming a fully known initial state or a closed set of predefined objects. Across three open-world egocentric benchmarks requiring active knowledge acquisition, \textsc{Plan2Sense} achieves higher success rates and improved efficiency over existing baselines while consistently avoiding undesirable and potentially unsafe states.

Large language model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model’s natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative information gain. Unlike prior methods that reward steps in isolation, PiCA defines process rewards as success probabilities dependent on the historical context. This approach identifies pivot steps (critical milestones in the search) as information peaks that significantly boost the likelihood of a correct final answer. By anchoring these step rewards to the final task objective, PiCA provides dense, pivot-aware and trajectory-dependent guidance while maintaining distributional consistency. Theoretically grounded in Potential-Based Reward Shaping (PBRS), PiCA consistently outperforms existing strong baselines across seven knowledge-intensive QA benchmarks, achieving 15.2% and 2.2% improvements for 3B and 7B models.

Realistic physical interaction is a cornerstone of embodied intelligence, yet obtaining high-fidelity tactile data remains significantly more expensive than visual data. This scarcity necessitates Visual-to-Tactile synthesis to bridge the Sim-to-Real gap. However, existing data-driven approaches often treat this as a naive image-to-image translation task, neglecting fundamental contact mechanics. Moreover, the inherent spatial misalignment in real-world visual-tactile datasets frequently forces generative models to average out spatial uncertainties, resulting in blurry and textureless outputs. To address these limitations, we introduce PhysTacGen, a physics-aware generation framework that enforces consistency between visual appearance and tactile mechanics. Our system makes three technical contributions. Firstly, we propose Group Tactile Policy Optimization (GTPO), a reinforcement learning alignment strategy that refines Large Multimodal Models to infer latent physical properties by rewarding physics-consistent reasoning chains. Secondly, we introduce a Semantic-Driven Data Curation and Visual Prior pipeline, leveraging DINOv2 to filter spatially misaligned data and extracting pure depth maps to decouple macro-geometry from surface texture. Finally, we present a physics-driven generative architecture based on Stable Diffusion XL (SDXL). It synthesizes tactile images via a ControlNet conditioned on GTPO-generated physical descriptions and depth-augmented visual priors. Extensive experiments demonstrate that PhysTacGen achieves state-of-the-art perceptual quality and significantly enhances grasp force prediction for zero-shot Sim-to-Real transfer.

Generating realistic human motion is a central yet unsolved challenge in video generation. Reinforcement learning (RL)-based post-training has emerged as a promising direction, yet its success critically depends on the quality of the reward signal. Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion, and often assign high scores to videos with floating bodies or physically implausible movements. To address this, we propose PhyMotion, a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility. Concretely, we recover SMPL body meshes from generated videos, retarget them onto a humanoid in the MuJoCo physics simulator, and evaluate the resulting motion along three axes: kinematic plausibility, contact and balance consistency, and dynamic feasibility. Each component provides a continuous and interpretable signal tied to a specific aspect of motion quality, allowing the reward to capture which aspects of motion are physically correct or violated. Experiments show that PhyMotion achieves stronger correlation with human judgments than existing reward formulations. When used for RL-based post-training, it consistently improves motion realism across both autoregressive and bidirectional video generators under both automatic metrics and blind human evaluation. Ablations further show that the three axes provide complementary supervision signals, while the reward preserves overall video generation quality with only modest training overhead.

Recent advancements in Large Language Model (LLM) agents have demonstrated strong capabilities in executing complex tasks through tool use. However, long-horizon multi-step tool planning is challenging, because the exploration space suffers from a combinatorial explosion. In this scenario, even when a correct tool-use path is found, it is usually considered an immediate reward for current training, which would not provide any reusable information for subsequent training. In this paper, we argue that historically successful trajectories contain reusable tool-transition patterns, which can be leveraged throughout the whole training process. Inspired by ant colony optimization where historically successful paths can be reflected by the pheromone, we propose Pheromone-Guided Policy Optimization (PhGPO), which learns a trajectory-based transition pattern (i.e., pheromone) from historical trajectories and then uses the learned pheromone to guide policy optimization. This learned pheromone provides explicit and reusable guidance that steers policy optimization toward historically successful tool transitions, thereby improving long-horizon tool planning. Comprehensive experimental results demonstrate the effectiveness of our proposed PhGPO.

Context-based offline meta-reinforcement learning (COMRL) has progressed almost entirely through better task representations: separating task identity from behavior-policy artifacts so that the latent reflects the task information alone. The implicit expectation has been that a clean representation will transfer to out-of-distribution (OOD) tasks. However, on an OOD task the encoder produces a latent outside the training support, where the policy has never been trained. We address this gap with Pessimistic Latent Task-aware Optimization (PLATO), which exposes the policy to off-support latents at training time. PLATO assumes a mild manifold hypothesis: task latents lie on a low-dimensional manifold, with OOD tasks further from the training centroid. It exploits this geometry by perturbing inferred latents outward from the centroid to synthesize counterfactual tasks; a learned decoder ensemble then rolls out short trajectories at the perturbed latent, and the policy is updated on the imagined transitions under a pessimism weight that down-weights steps where the ensemble is unconfident. We prove that the perturbation reaches off-support by a controllable margin, that the epistemic disagreement at the perturbed latent is non-vanishing, and that the OOD generalization gap is bounded by the same perturbation reach. On eight MuJoCo continuous-control benchmarks, PLATO consistently improves out-of-distribution returns over strong COMRL baselines while remaining competitive in-distribution.

Bayesian persuasion, a central model in information design, studies how a sender, who privately observes a state drawn from a prior distribution, strategically sends a signal to influence a receiver's action. A key assumption is that both sender and receiver share the precise knowledge of the prior. Although this prior can be estimated from past data, such assumptions break down in high-dimensional or infinite state spaces, where learning an accurate prior may require a prohibitive amount of data. In this paper, we study a learning-based variant of persuasion, which we term persuasive prediction. This setting mirrors Bayesian persuasion with large state spaces, but crucially does not assume a common prior: the sender observes covariates $X$, learns to predict a payoff-relevant outcome $Y$ from past data, and releases a prediction to influence a population of receivers. To model rational receiver behavior without a common prior, we adopt a learnable proxy: *decision calibration*, which requires the prediction to be unbiased conditioned on the receiver's best response to the prediction. This condition guarantees that myopically responding to the prediction yields no swap regret. Assuming the receivers best respond to decision-calibrated predictors, we design a provably efficient algorithm that learns a decision-calibrated predictor within a randomized predictor class that optimizes the sender's utility. In the commonly studied single-receiver case, our method matches the utility of a Bayesian sender who has full knowledge of the underlying prior distribution. Finally, we extend our algorithmic result to a setting where receivers respond stochastically to predictions and the sender may randomize over an infinite predictor class.

Reinforcement learning (RL) is well known to be data-intensive, and recent works have proposed leveraging data from similar systems to improve sample efficiency. In this work, we focus on the collaborative Linear Quadratic Regulator (LQR) setting and study the problem of learning under heterogeneous system dynamics. Due to the presence of a heterogeneity-induced additive bias, most existing collaborative methods are suitable only for low heterogeneity regimes and exhibit suboptimal performance under large heterogeneity. Based on the principle of Thompson sampling (TS), we propose an algorithm that, by leveraging data from other agents, yields a \emph{personalized} controller for every agent without incurring any additive heterogeneity-induced bias, i.e., with sublinear Bayes regret even under large heterogeneity. Under high heterogeneity regimes, we establish that our algorithm incurs $\tilde{\mathcal{O}}( T^{1-0.5\epsilon}\sqrt{\Delta})$ cumulative regret, where $T$ denotes the time horizon, $\epsilon\in[0,1]$ is a user-defined personalization parameter, and $\Delta$ denotes an upper bound on the maximum dissimilarity among the agents' dynamics. Our algorithm and analysis also generalize the special case of no heterogeneity. In particular, under no heterogeneity, we establish that our algorithm incurs $\mathcal{O}(\sqrt{T/M})$ cumulative regret. From a distributed implementation perspective, our method incurs only logarithmic communication overhead. Additionally, our algorithm outperforms methods that do not personalize data from other agents and, in certain regimes, also outperforms methods that do not utilize any data from other agents.

Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts during causal discovery has been recognized as a critical deficit. The underlying mechanisms of this phenomenon remain incompletely understood, as existing benchmarks only measure response accuracy without revealing the sources and extent of the deficit. We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis, probing causal discovery through five controlled configurations that systematically manipulate visual and textual modalities to decompose their respective contributions to model behavior and dissect the failure modes. Evaluating 17 mainstream LMMs, we find that models faithfully perceive video content yet systematically underexploit it during causal reasoning. We further observe that stronger post-training amplifies rather than mitigates textual prior reliance, and that higher baseline performance correlates with greater fragility under perturbation. To address these, we propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment, which augments GRPO by explicitly pushing the policy away from a prior-only counterfactual teacher induced by visual corruption. Specifically, ADPO maximizes the divergence between the policy distributions conditioned on the original and visually corrupted inputs, thereby forcing the model to ground its reasoning in visual evidence rather than textual shortcuts. Extensive experiments show that ADPO improves visual engagement without sacrificing fundamental comprehension, thus offering a preliminary step toward reliable causal discovery.

Reinforcement-learning-trained agents for retrieval-augmented generation retrieve content (passages, knowledge-graph fragments, or hyperedges) and supervise training with outcome rewards on the final answer. Across these paradigms the reasoning route through retrieved content never leaves the language model's hidden state, conflating declarative knowledge with the procedural knowledge that recurs across queries of the same logical type; content-only methods consequently plateau as reasoning depth grows. We then introduce PatternBloom, an agentic RAG framework that shifts the unit of retrieval from content (what to read) to logic (how to reason). A first RL stage scores the agent's constructed evidence graph by a frozen oracle's information gain through the Information-Density Reward (IDR), a size-normalized mutual-information surrogate. High-reward trajectories are distilled into a Graph Pattern Memory (GPM) of type-abstracted reasoning skeletons, and a second RL stage uses the Pattern-Augmented Reward (PAR) to couple policy to memory, turning procedural reasoning into a learnable, externalized structural prior. A 7B PatternBloom outperforms 27 baselines by +15.0 Avg-OOD EM, with the gain compounding with reasoning depth precisely because procedural knowledge, once distilled, is reused rather than re-derived at every query.

Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that encouraging exploration during LLM reinforcement learning can improve downstream performance. However, methods for controlling exploration often rely on heuristics like clipping or temperature scaling that are unable to fundamentally change token-level distributions, which might limit exploration. Here, we explore controlling exploration via variational learning, where a distribution over neural network parameters is learned via noisy optimization, with parameters sampled from an approximate posterior. We introduce Perturbed Parameter Policy Optimization (3PO), where the amount of noise that is added to model parameters functions as an additional control lever that can be tuned for exploration. We show that using multiple parameter samples within a batch performs better than using a single sample. When using multiple parameter samples in group-based methods like GRPO, we find that calculating advantages across rollouts from all parameter samples performs best. We call this Chunked Perturbed Parameter Policy Optimization (C3PO). We show empirically on a range of math reasoning benchmarks and LLMs that using multiple parameter samples can improve downstream performance, especially on harder benchmarks like AIME. Overall, our work presents evidence that parameter-space exploration can improve LLM reinforcement learning.

Entropy-regularized optimization problems arise in various areas of machine learning, including mean-field neural networks, variational inference, and reinforcement learning. Mean-field Langevin dynamics (MFLD) is a dynamics capable of sampling from the optimal solution of such problems under appropriate conditions, and has been the subject of extensive recent research. As machine learning models grow in scale and parameter dimension, computational efficiency becomes increasingly important, especially in reducing the adaptive complexity of computation of MFLD, that is, the number of sequential rounds they require. In this work, we initiate the study of the adaptive complexity of MFLD and provide the first theoretical evidence that MFLD can indeed be accelerated through parallelism. In particular, we provide polylogarithmic convergence guarantees for both the infinite-particle and finite-particle setting under the log-Sobolev inequality.

Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video understanding. However, existing native-RL methods dispatch tool calls sequentially (i.e., one per turn): a single wrong crop propagates errors without peer correction, multi-turn tool calls corrupt context, and inference cost scales linearly with the number of turns. We introduce **ParaVT**, the first multi-agent end-to-end RL-trained framework for **Para**llel **V**ideo **T**ool calling, dispatching multiple time-window crops in a single turn for cleaner context and better fault tolerance. Yet applying standard RL to ParaVT reveals an obstacle we term the *Tool Prior Paradox*: the pretrained tool priors that enable tool exploration also destabilize cold-started structural format and expose the skip-tool reward shortcut under temperature sampling. A cross-model contrast on a weaker-prior LMM supports this claim: format stays stable but RL elicits zero tool calls, indicating that prior strength is the shared driver of both format collapse and tool exploration. We propose **PARA-GRPO** (**P**arseability-**A**nchored and **R**atio-g**A**ted **GRPO**), which augments standard RL with two complementary mechanisms: (i) a *targeted format reward* applied only at the structural-token positions most prone to collapse, and (ii) a *per-prompt frame-budget randomization* that creates training prompts where calling the tool yields a measurable reward signal over skipping it. Across six long-video understanding benchmarks, ParaVT improves over the Qwen3-VL baseline by $+7.9\%$ on average, with PARA-GRPO lifting training-time format compliance from $0.13$ to $0.64$. As tool capabilities become increasingly internalized in modern LMMs, RL must cooperate with the resulting priors, and ParaVT offers a general recipe for agentic RL. Code, data, and model weights will be released.

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose \textsc{Precise}, a new stochastic sampler that balances effective exploration with stability. Crucially, \textsc{Precise} keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1--53.2\% less wall-clock training time to match the best in-domain performance of prior samplers.

Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive. We introduce PO-PDDL, a symbolic formulation of POMDPs that preserves the relational structure and LLM-friendly syntax of the Planning Domain Definition Language (PDDL), while explicitly modeling partial observability, stochasticity, and beliefs. Building on this formulation, we propose a demonstration-driven pipeline for learning PO-PDDL models. The proposed method reconstructs latent symbolic state trajectories from real-robot execution videos, identifies partial observability via inconsistencies between inferred states and visual observations, and learns stochastic transition and observation models accordingly. The resulting PO-PDDL domains are reusable across tasks and enable online belief-space planning under both perception and execution uncertainty. Experiments on real-world long-horizon manipulation tasks show that our method consistently outperforms existing PDDL and POMDP model-learning approaches, achieving robust task planning under uncertainty with significantly lower planning cost.

Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a fundamental challenge to multi-agent reinforcement learning (MARL), which typically assumes fixed state and action spaces. Existing methods address openness only partially: padding and masking approaches introduce artificial bounds, while recent graph-based or hypergraph methods handle one dimension of openness but still depend on restrictive assumptions. In this paper, we introduce Pointer Learner for Agent and Task Openness (PLATO), a pointer-network-based actor combined with a centralized graph neural network (GNN) critic, trained with multi-agent proximal policy optimization under a centralized training and decentralized execution paradigm. Our pointer-based actor outputs distributions directly over the current task set. This directly supports changing action spaces without masking or retraining. Our GNN critic encodes agent–task interactions as a graph that changes shape with task and agent composition. Together, these components consider AO and TO without the boundedness of existing approaches. We formalize PLATO in a Task-and-Agent-Open Markov Game (TaAgO-MG), extending prior task-open formulations, and prove it is well-defined over the resulting unbounded state and action spaces. We evaluate PLATO with the Methods for Open Agent Systems Evaluation Initiative (MOASEI) wildfire suppression domain, an environment designed for open multi-agent system evaluation, and we demonstrate strong performance and more consistent zero-shot generalization than state-of-the-art baselines in OASYS.

Machine learning is increasingly used for autonomous navigation, yet safety regulations governing safety-critical AI applications require rigorous datasets and protocols to evaluate learned planners on terrain-aware routing. Existing path-planning benchmarks address this only partially: synthetic grids offer algorithmic control without geographic realism, while Geographic Information System (GIS) resources provide real terrain without controllable obstacles or standardised baselines. To close this gap and steer research toward more trustworthy AI-based planners, especially in line with EASA and FAA guidance on AI, we introduce **PASSAGE**, an open-source benchmark and dataset that reframes constrained terrain path planning as a *controlled trustworthiness-oriented evaluation harness* rather than a static dataset. PASSAGE is sampled from a well-defined Operational Design Domain (ODD) built on JAXA ALOS AW3D30 elevation at its native 30 m/pixel resolution, and is derived into seven input-tensor resolutions from 64×64 to 4096×4096 pixels, totalling *4.4 million samples* for ≈ *2.43 TB* of compressed data. Each sample is a real-terrain cost grid annotated with start and goal markers, procedurally generated super-ellipse obstacles, and exact A* path labels under three physically interpretable cost models. The release pairs this dataset with a deterministic generation pipeline, a geographic hold-out, ODD-coverage diagnostics, and a rigorous evaluation protocol — a shift from *dataset collection* towards *auditable benchmark design* that provides a rare level of experimental control for studying robustness, generalisation, and other trustworthiness properties of safety-critical embedded AI. PASSAGE thereby offers a common surface for comparing AI-based path planners, including two dense-vision approaches we introduce as illustrative examples (path-mask segmentation and depth-estimation-inspired cost-to-go regression), with graph-neural and reinforcement-learning families as natural future extensions. Although motivated by aerospace trustworthiness requirements such as completeness, correctness, and representativeness, PASSAGE broadly supports trustworthy machine learning across robotics, autonomous navigation, and other safety-critical planning domains. Code (anonymous repository) and dataset (anonymous mirror) are released openly under permissive licences.

Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a forgiving \emph{region-tolerant} paradigm, where many nearby pixels inside the same component remain valid. Precise geometric construction breaks this assumption: actions must land on points in continuous canvas space rather than tolerant regions. Because geometric primitives carry ontological dependencies, a local coordinate error can induce cascading topological failures that distort downstream objects and invalidate the final construction. We identify this regime as \emph{precision-sensitive GUI tasks}, requiring point-level accuracy, geometry-aware verification, and robustness to dependency-driven error propagation. To benchmark it, we introduce \textsc{PAGE} Bench, with 4{,}906 problems and over 224K process-supervised, pixel-level GUI actions. We further propose \textsc{PAGER}, a topology-aware agent that decomposes construction into dependency-structured planning and pixel-level execution. Pixel-grounded supervised tuning establishes executable action grammar, while precision-aligned reinforcement learning mitigates rollout-induced exposure bias through state-conditioned geometric feedback. Experiments reveal a pronounced ``Semantic-Execution Gap'': general multimodal models can exceed 88\% Action Type Accuracy yet remain below 6\% Task Success. \textsc{PAGER} closes this gap, delivering $4.1\times$ higher Task Success than the strongest evaluated general baseline and raising Step Success Rate from below 9\% for GUI-specialized agents to over 62\%, establishing a new state of the art for point-precise GUI control.

Large language models have become drivers of evolutionary search, but most systems rely on a fixed, prompt-elicited policy to sample next candidates. This limits adaptation in practical engineering and research tasks, where evaluations are expensive, and progress depends on learning task-specific search dynamics. We introduce PACEvolve++, an advisor-model reinforcement learning framework for test-time policy adaptation in evolutionary search agents. PACEvolve++ decouples strategic search decisions from implementation: a trainable advisor generates, assesses, and selects hypotheses, while a stronger frontier model translates selected hypotheses into executable candidates. To train the advisor under non-stationary feedback, we propose a phase-adaptive approach that adapts its optimization strategy to different phases of the evolutionary process. Early in evolution, it uses group-relative feedback to learn broad search preferences; later, as reward gaps compress, it emphasizes best-of-$k$ frontier contribution to support stable refinement. Across expert-parallel load balancing, sequential recommendation, and protein fitness extrapolation, PACEvolve++ outperforms the state-of-the-art evolutionary search framework with frontier models, achieving faster convergence and stabilizing test-time training during evolutionary search.