NeurIPS 2026 Papers

End-to-end full-duplex speech models have brought open-source machine conversation close to human fluency, yet existing systems fall short of real-world deployment in two entangled respects: long-context conversational robustness and multi-party interaction capability. Realistic settings, including meetings, group lessons, family dinners, and social-robot reception, are inherently long-horizon and multi-party at the same time, requiring a single model to perceive, attribute, contextualize, and respond across multiple speakers over extended durations. Progress along these axes is bottlenecked by both data and evaluation. On the data side, open multi-party conversational speech corpora total only a few hundred hours and are not designed for codec-frame-level full-duplex modeling. On the evaluation side, existing long-audio benchmarks focus on passive listening, while existing speech-to-speech benchmarks remain dyadic and short. In this work, we extend the Moshi paradigm along long-horizon and multi-party axes simultaneously, in both English and Chinese, with three contributions. First, we release an open data engine and a 57.6 k-hour corpus for long, multi-party, bilingual full-duplex dialogue. The engine produces parallel-stream audio with controllable length, participant count, conversational dynamics (turn-taking, overlap, backchannels, interruption, addressee shifts, long-range co-reference), and language (English, Chinese, and intra-sentential code-switching), exceeding all prior open multi-party conversational speech corpora by more than an order of magnitude. Second, we introduce MultiTalkBench, the first benchmark to jointly evaluate long-form full-duplex dialogue with an average duration of 32.6 minutes, multi-party, and bilingual full-duplex dialogue, with explicit probes for long-range entity tracking, topic coherence, and addressee selection. Third, we train a bilingual Moshi-style full-duplex model on the released corpus that sustains coherent multi-party English-Chinese conversation over extended durations, substantially outperforming open-source baselines including Moshi, MiniCPM-o-4.5, and Qwen3-Omni-30B-A3B-Instruct.

A striking case of goal misgeneralization was previously observed in OpenAI's Minecraft agent VPT: it killed villagers standing under some leaves, mistaking them for trees. Although this agent was released publicly, enabling white-box interpretability research, few open-weight model organisms of misalignment exist outside the LLM space. In this work, we release MultiSTEVE-1s -- a model zoo of 140 fine-tuned versions of VPT, over 1,000 training checkpoints, and an interpretability suite for analysing them. Specifically, we use the STEVE-1 training procedure to add instruction-following capabilities to VPT with fixed hyperparameters and controlled variations in training randomness. We demonstrate the utility of MultiSTEVE-1s by showcasing the research it enables. First, for some training runs, the only difference is a least-significant bit flip in a single initialised weight. Others differ in the full randomness for weight initialisation and data. Yet, the single bit-flip setting produces agents that act nearly as differently from each other as the full randomness ones. Second, we use our interpretability suite to show that several known VPT attention heads retain their roles after STEVE-1 fine-tuning, while attention strength to the same behaviourally meaningful frame can vary substantially across agents and checkpoints. Finally, even though the agents are similarly capable in in-distribution tasks, the out-of-distribution behaviour of villager killing can differ substantially between them -- in one setting, an agent kills villagers less than 5\% of the time, while another agent kills them nearly 50\% of the time. Our results show the value of studying multiple similarly trained agents, rather than acting like a behavioural biology lab with only one rat.

Consistency models achieve fast image synthesis by chaining a small number of neural evaluations along a diffusion trajectory, yet the distribution error of $N$-step sampling for $N \geq 3$ has lacked a rigorous characterisation. We establish a tight Wasserstein-$p$ error bound for arbitrary $N$: the total error equals a Lipschitz-weighted sum of per-step local consistency errors, $\sum_{k=1}^{N} L_x^{N-k} \delta_k$, making the propagation mechanism explicit. From this bound we derive a closed-form optimal step count $N^{\star}$ whose structure bifurcates on whether the spatial Lipschitz constant $L_x$ exceeds one: for $L_x > 1$, exponential error growth yields $N^{\star} \approx (\ln L_x)^{-1} \log(\beta\gamma(L_x-1)/(c \ln L_x))$; for $L_x < 1$, geometric-series saturation gives $N^{\star} \approx (\beta\gamma(1-L_x)/(c \, |\ln L_x|))^{1/(\gamma+1)}$. The two-regime structure accounts for ECT's best FID of $2.73$ at $N=2$: with $L_x \approx 0.85 < 1$ (Case 2), the formula gives $N^{\star} \approx 1.7$. Experiments on CIFAR-10 reproduce the predicted U-shaped FID curve with $N^{\star} = 8$ on a capacity-constrained model in which error accumulation is easier to see.

Wearables are widely used for mobile health monitoring, and photoplethysmography (PPG) is a key sensing modality for heart rate and related physiological measurements. However, public in-the-wild PPG datasets remain largely wrist-centric or limited to short, controlled studies, constraining research on emerging wearable form factors. We present Multi-site PPG, an in-the-wild physiological dataset collected from four custom-developed unobtrusive wearables: a smart earring, ring, watch, and necklace. Each device records green and infrared reflective PPG, 3-axis acceleration, and temperature with timestamps for cross-device alignment, while a Polar H10 chest strap provides reference electrocardiogram (ECG). Participants wore the devices for one to multiple days during daytime activities while continuing their normal routines. The dataset contains over 350 hours of raw data and 230–290 hours of preprocessed, modeling-ready 8-second windows data per wearable. We benchmark heuristic, supervised, and self-supervised heart-rate estimation methods, showing substantial body-site differences: the best methods achieve mean absolute errors (MAEs) of 2.30 bpm on the earring, 5.13 bpm on the ring, 8.37 bpm on the watch, and 8.68 bpm on the necklace. We further analyze motion effects and evaluate multi-site and PPG–accelerometer fusion, demonstrating the dataset’s value for robust physiological sensing across emerging wearable form factors.

Watermarking has emerged as a fundamental mechanism for tracing the provenance of Large Language Model (LLM) outputs. While multi-bit watermarks are highly desirable for embedding rich metadata, they suffer from an inherent trade-off between statistical detectability and text quality degradation. Crucially, existing multi-bit schemes lack theoretical quality guarantees, leaving them susceptible to unbounded semantic distortion. To address this, we introduce CSD, the first multi-bit watermarking framework with certified semantic distortion bounds. In CSD, we derive a closed-form upper bound on the Kullback-Leibler (KL) divergence, mathematically guaranteeing strict limits on semantic distortion at every generation step. Furthermore, rather than relying on static payloads, CSD employs a dynamic payload to maximize statistical detectability. Extensive empirical evaluations across multiple datasets demonstrate that CSD achieves robust detectability while maintaining provably safe text generation.

Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase concurrently, their changes can silently conflict and inconsistent views lead to integration failures. Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent), but this defers conflict resolution to a post-hoc merge step where recovery is expensive. In this paper, we propose STORM, i.e., STate-ORiented Management for multi-agent collaboration. Specifically, STORM manages agent states by mediating their interactions with the shared workspace, ensuring that each agent operates on a consistent view of the codebase and that conflicting edits are detected and resolved at write time.We evaluate STORM on Commit0 and PaperBench across multiple LLMs. STORM outperforms the git-worktree-based multi-agent baseline by +18.7 on Commit0-Lite and +1.4 on PaperBench, while achieving comparable or better cost efficiency. Combined with single-agent runs, STORM reaches highest scores of 87.6 and 78.2 on the two benchmarks respectively, suggesting that explicit state management is a more effective foundation for multi-agent collaboration than workspace isolation. STORM can also be plugged into any multi-agent system. Our code is available at \url{https://anonymous.4open.science/r/STORM-Mutli-Agent}.

Conformal prediction constructs prediction sets with finite-sample coverage guarantees, but its calibration stage is structurally constrained to a scalar score function and a single threshold variable — forcing shapes of prediction sets to be fixed before calibration, typically through data splitting. We introduce multi-variable conformal prediction (MCP), a framework that extends conformal prediction to vector-valued score functions with multiple simultaneous calibration variables. Building on scenario theory as a principled framework for certifying data-driven decisions, MCP unifies prediction set design and calibration into a single optimization problem, eliminating data splitting without sacrificing coverage guarantees. We propose two computationally efficient variants: RemMCP, grounded in constrained optimization with constraint removal, which admits a clean generalization of split conformal prediction; and RelMCP, based on iterative optimization with constraint relaxation, which supports non-convex score functions at the cost of possibly greater conservatism. Through numerical experiments on ellipsoidal and multi-modal prediction sets, we demonstrate that RemMCP and RelMCP consistently meet the target coverage with prediction set sizes smaller than or comparable to those of baselines with data split, while considerably reducing variance across calibration runs — a direct consequence of using all available data for shape optimization and calibration simultaneously.

Mathematical optimization drives decisions in supply chains, logistics, energy, and scheduling, but translating natural-language problems into solver-executable formulations remains a bottleneck. While frontier models show promise for this task, many deployments require small language models (SLMs) that run locally under privacy, latency, and cost constraints. Existing SLMs are limited by noisy data, ambiguous benchmarks, and one-shot inference that ignores the iterative, feedback-driven nature of optimization modeling. We introduce \textsc{OptiMind}, a framework for improving SLMs through formulation-centric data cleaning, class-conditional priors, and multi-turn reinforcement learning with solver feedback. \textsc{OptiMind} repairs ambiguous problems, regenerates solution trajectories, audits benchmark labels, constructs accepted objective-value sets, and distills class-level hints from recurring formulation errors. It then trains models to formulate, execute, and revise GurobiPy programs using solver-verified correctness as reward. On expert-cleaned IndustryOR, Mamo-Complex, and OptMATH benchmarks, a 20B \textsc{OptiMind-RL} model outperforms strong open-source baselines and reaches frontier-model performance under the same protocol. Our results suggest that optimization formulation is better treated as an interactive solver-grounded decision process than as one-shot code synthesis. We release our inference framework, cleaned benchmarks, and sample error analyses at \url{https://anonymous.4open.science/r/OptiMind-NeurIPS-1DB020}, with full data and model to follow.

Reinforcement learning with verifiable rewards (RLVR) plays a pivotal role in improving the reasoning ability of large language models. However, widely used PPO surrogate objectives are fundamentally *local*, as they rely on a local approximation of the exact policy gradient objective. While this approximation improves stability by reducing the variance induced by importance sampling, it also introduces structural bias into the surrogate objective, which must be controlled through trust region mechanisms. In this work, we introduce the $N$-step forward trace, which augments the PPO surrogate objective using the cumulative likelihood ratio of the next $N-1$ tokens. Building on this idea, we propose $N$-Step Forward-Trace Policy Optimization (NFPO), a practical RLVR algorithm that integrates the $N$-step forward trace into the masked policy gradient framework. NFPO provides a continuous bridge between the PPO surrogate objective and the exact policy gradient objective, offering a principled mechanism for controlling the bias–variance trade-off. Our theoretical analysis shows that, with an appropriate choice of $N$, the proposed objective yields a tighter policy-improvement bound than the standard PPO surrogate. Experiments on comprehensive reasoning benchmarks demonstrate that NFPO consistently improves performance, supporting our theoretical findings.

Long-horizon planning often requires composing familiar local transitions while remaining grounded in a specified goal. We study this setting from single-stage data: on a controlled no-skip graph benchmark, training provides only adjacent-stage demonstrations while evaluation requires composing them on unseen long-horizon start–goal pairs; an event-chain diagnostic decomposes success into legality, stage-bridging, and goal-conditioned termination. Across a minimal Transformer, Qwen2.5-3B, and an external validation on MuSiQue multi-hop QA, supervised fine-tuning (SFT) learns local transitions but degrades with horizon, with failures localized to stage-bridging. Reinforcement learning (RL) narrows this composition gap, especially at longer horizons, but unanchored RL drifts—producing valid stage progress while ignoring the instructed target. Stable gains require two complementary forms of anchoring: instruction-style prompting strengthens prompt-side goal-conditioning, especially at shorter horizons, whereas KL regularization to the SFT reference policy prevents RL-induced drift across horizons; reward shaping mainly provides denser credit. Finally, we identify a Decomposition Paradox: models trained only on long compositions can reach intermediate targets yet fail the corresponding prefix subtasks because stopping at instructed intermediates is never supervised.

Discovering object-centric representations from images can significantly enhance the robustness, sample efficiency and generalizability of vision models. Works on images with multi-part objects typically follow an implicit object representation approach, which fail to recognize these learned objects in occluded or out-of-distribution contexts. This is due to the assumption that object part-whole relations are implicitly encoded into the representations through indirect training objectives. We address this limitation by proposing a novel method that uses explicit graph representations for parts and introduce a new co-part algorithm for multi-part object discovery. The part representations are refined with a part-centric regularization objective. We then introduce three benchmarks to evaluate the robustness of object-centric methods in recognizing multi-part objects within occluded and out-of-distribution settings. Experimental results on simulated, realistic, and real-world images show marked improvements in the quality of discovered objects compared to state-of-the-art methods, as well as the accurate recognition of multi-part objects in occluded and out-of-distribution contexts. We also show that the discovered object-centric representations can more accurately predict key multi-part object properties in a downstream task, highlighting the potential of our method to advance the field of object-centric representations.

Computational RNA design methods routinely evaluate designed sequences by refolding them with the same structure-prediction model used during optimization, measuring agreement with the design target. While scalable, this practice carries a fundamental risk: when optimization and evaluation share the same underlying model, high scores can reflect model-specific idiosyncrasies rather than genuine structural quality. To characterize the severity and mechanism of this problem, we audited nine RNA design methods spanning four algorithmic paradigms, evaluating approximately 11,000 sequences against predictors from two independent model families: physics-based thermodynamic models and machine-learning models, alongside five tertiary-structure predictors and large-scale SHAPE chemical-mapping data. We find that 78.1% of designs produced by single-objective optimization pass one predictor yet fail another, while ensemble-based methods reduce this disagreement 30-fold. A controlled experiment identifies optimization objective breadth, not search strategy, as the primary driver of this fragility. Cross-predictor disagreement carries a calibrated experimental signal: lower disagreement predicts higher SHAPE accuracy across 40,000 sequences, yet remains null-to-anti-predictive for biological function, establishing a clear scope boundary. We release **ACCORD** (**A**cross-oracle **C**alibration for **CO**mputational **R**NA **D**esign), a benchmarking workflow that reports per-predictor scores, experimentally calibrated uncertainty tiers, and explicit warnings for invalid use cases, providing the community with a principled foundation for RNA design evaluation.

Multi-objective reinforcement learning (MORL) is a fundamental problem for modern AI, with applications spanning robotics, LLMs, and reasoning. A central challenge is to learn policies that balance competing objectives, such as speed versus energy in robotics, or helpfulness versus honesty in alignment. Optimal policies can vary sharply with the preferred objective weights, and the severity of this variation depends crucially on the degree of misalignment among objectives, making per-preference learning sample-inefficient. To formalize this, we introduce an *objective-conflict coefficient* and use it to derive near-optimal regret bounds for online MORL that quantify the impact of misalignment on learning efficiency. Motivated by this analysis, we propose *routed ensemble policy learning*, an algorithm that maintains a small set of basis policies and dynamically routes trajectories to the policy with the highest potential reward. We further design a scalable, kernel-based attribution algorithm that estimates how feedback signals from one set of trajectories influence policy learning on others. Unlike existing attribution methods, our approach captures nonlinear interactions, such as synergy and antagonism between trajectories, to explain objective conflict. We extensively evaluate our approach across diverse environments and benchmarks: routed ensembles improve average performance by 4.3\% over MORL baselines on several environments from the Meta-World and MO-Gymnasium benchmarks, and kernel-based attribution improves correlation with leave-one-out analysis over existing baselines by 50\%. When applied to downstream task selection, kernel-based attribution yields a 27\% improvement in reward over baseline attribution methods.

Many decision-making problems involve multiple objectives, where actions affect several performance metrics, fairness criteria, or safety constraints. We study multi-objective causal bandits with multiple reward nodes, where actions correspond to interventions on subsets of variables in a causal graph and performance is evaluated through Pareto optimality. Existing approaches to multi-objective bandits typically define optimality at the level of individual actions, using pairwise dominance or scalarization. In contrast, randomized decision rules induce convex combinations of action-level reward vectors, so the relevant achievable set is the convex hull of these rewards. Thus, an intervention may be suboptimal even if no single intervention dominates it, because it can be dominated by a randomized policy over other interventions. We formalize this policy-level phenomenon and show that it has consequences for both causal action-space reduction and online learning. First, we provide a necessary-and-sufficient graphical characterization of possibly Pareto-optimal minimal intervention sets (PPOMISs). Our characterization yields a minimal, sound, and complete candidate intervention family from the graph alone, correcting prior formulations that may include intervention sets that are never Pareto-optimal under any compatible structural causal model. Second, over this reduced intervention space, we design an online UCB-style algorithm that eliminates actions using dominance tests against convex combinations of other actions, and prove logarithmic gap-dependent Pareto regret. Finally, we study constrained multi-objective causal bandits, where feasibility and optimality may be realized only with randomized policies, and develop an online UCB-style constrained bandit algorithm with sublinear regret and constraint-violation guarantees.

We study stochastic multi-objective optimization when each objective may be non-smooth and non-convex. We introduce the notion of $(\delta,\epsilon)$-Pareto Goldstein stationary points (PGSP) to characterize the convergence of solving multi objective optimization. The $(\delta,\epsilon)$ generalizes the definition of $(\delta,\epsilon)$-Goldstein stationary point for single objective non-smooth non-convex optimization and the $\epsilon$-Pareto stationary point for solving multi objective optimization with smooth objectives. We propose the multi-gradient-free method (MGFM), which finds $(\delta,\epsilon)$-PGSP with $\tilde{\mathcal{O}}(m^2d^{3/2}\delta^{-1}\epsilon^{-4})$ oracle complexity to the stochastic function values, where $m$ is the number of objectives and $d$ is the problem dimension. We further propose MGFM+, a faster multi-gradient-free method based on variance reduction, which improves the complexity to $\tilde{\mathcal{O}}(m^2d^{3/2}\delta^{-1}\epsilon^{-3})$. These provide the first non-asymptotic analysis for multi-nonsmooth-nonconvex-objective optimization. \end{abstract}

Realizing stable neural decoding over extended periods remains a significant challenge, primarily because invariant task-related neural dynamics are inextricably entangled with inherent signal non-stationarity and the physical drift of electrode-neuron interfaces. This work introduces LNDN (Long-term Neural Decoding Network), a hierarchical framework designed to decouple category-specific neural dynamic manifolds from representational drift, sustaining decoding precision without periodic recalibration. The proposed architecture addresses representational drift through an integrated tri-level alignment strategy. At the physical feature level, a decoupled representation and dynamic gating module isolates the physical identity of neurons from their transient states, adaptively filtering stochastic neural noise. This is further strengthened at the decision level by a Mixture-of-Experts (MoE) architecture, which employs a parallel soft-voting mechanism to suppress high variance induced by local representational distortions. Finally, at the manifold level, Adaptive Batch Normalization (AdaBN) and latent contrastive learning, combined with second-order correlation alignment, explicitly anchor the geometric consistency of the low-dimensional neural manifold over a period of months. Systematic evaluations on a longitudinal olfactory dataset, involving 9 mice performing a four-odor decoding task, demonstrate the efficacy of this approach. When trained exclusively on data from the initial four weeks, LNDN maintains an average accuracy of 83.67\% on completely unseen tests spanning the subsequent eight weeks, significantly outperforming mainstream domain adaptation and advanced neural decoding baselines. This framework offers a scalable, "set-and-forget" solution for robust, long-term invasive brain-computer interface applications.

Partially Observable Markov Decision Processes (POMDPs) are systems in which one agent interacts with a stochastic environment, and receives only partial information about the current state. In a multi-environment POMDP (MEPOMDP), the initial state is unknown, and assumed to be adversarially chosen. In this work we focus on computing the optimal value and policy in MEPOMDPs with finite-horizon objectives. That problem is known to be PSPACE-complete in POMDPs. Our main results are as follows: (1) we establish that it is also PSPACE-complete in the more general setting of MEPOMDPs; (2) we present a practical algorithm and evaluate it on classical benchmarks, significantly outperforming the only previously known algorithm.

Randomized Smoothing (RS) is a principled and widely adopted approach for certifying the robustness of black-box models, such as neural networks, against adversarial perturbations. We propose an optimization perspective that unifies several prior randomized smoothing certificates. We then show how to reduce the underlying high-dimensional worst-case optimization problem to an equivalent two-dimensional formulation under a double- or multi-sampling scheme, enabling efficient solutions via convex optimization. By exploiting additional information about the variance of the smoothed classifier across different smoothing distributions, we derive certified bounds that improve upon standard certificates. We show results on both classification and regression tasks.

We study multi-armed bandits (MABs) augmented with best-action queries, in which the learner may additionally query an oracle that reveals the best arm in the current round. This setting was recently characterized by Russo et al. [2024] in the full-feedback model, where the learner observes the rewards of all arms after each round. They show that, in both stochastic and adversarial environments, $k$ best-action queries reduce the optimal $\widetilde{\mathcal{O}}(\sqrt{T})$ regret to $\widetilde{\mathcal{O}}(\min\{T/k,\sqrt{T}\})$. Whether this improvement extends to the more realistic bandit-feedback model---where the learner observes only the reward of the played arm---was left as an open problem. We fully resolve this question. When rewards are stochastic but correlated among arms, we show that the full-feedback result does not carry over: any algorithm must incur regret at least $\Omega(\sqrt{T-k})$. This lower bound directly extends to adversarial environments. On the positive side, we show that $\widetilde{\mathcal{O}}(\min\{T/k,\sqrt{T-k}\})$ regret is still achievable when rewards are stochastic and i.i.d., and establish a matching lower bound, up to logarithmic factors. Together, these results provide a complete characterization of the benefits of best-action queries in the bandit-feedback model.