NeurIPS 2026 Papers

Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments. Existing approaches either rely on training data with ground truth annotations or require advanced proprietary language models (LMs) to synthesize environments that keep fixed once created. In this work, we propose TRUSTEE, a cost-friendly method for training tool calling agents with dynamic environments fully simulated by free open-source LMs that can be as small as 8B, including task generation, user simulation, tool simulation and trajectory evaluation, paired with an adaptive curriculum learning mechanism that controls task difficulty during training. Our empirical results show that TRUSTEE outperforms baselines which require extra external resources in most cases. These confirm that, with a sufficiently sophisticated design, even simulated environments with a local 8B LM as the backbone could set a strong baseline for tool learning. We hope our proposed paradigm could democratize tool learning and inspire future research on environment scaling with limited resources.

Multi-Task Learning (MTL) is a fundamental problem in machine learning that has been extensively studied over the past decade. Recently, a variety of optimization-based MTL approaches have been proposed to jointly learn multiple tasks by modifying the optimization trajectory. In this paper, we argue that the design of mainstream optimization-based MTL methods implicitly assumes compatibility with momentum-free optimizers, which may limit the understanding of their effectiveness in modern training regimes. In practice, the instantaneously derived gradients from MTL operations contribute only marginally to the final parameter updates when momentum is present, resulting in an amortized rather than instant de-conflicting effect. Moreover, this amortized behavior can be further degraded under high-curvature optimization dynamics. To address this issue and enable the effective integration of mainstream MTL methods with advanced optimizers (e.g., Adam and Muon), we propose \texttt{APT} (Applicability of advanced oPTimizers), a lightweight framework featuring an adaptive momentum mechanism that balances the trade-off between instant and amortized de-conflicting. Furthermore, we show that the Muon optimizer can be interpreted as an implicit MTL learner, and we introduce a lightweight direction preservation strategy to better align with its orthogonalization process. Extensive experiments across four standard MTL benchmarks demonstrate that \texttt{APT} consistently enhances existing MTL approaches, yielding substantial performance gains.

The first-moment buffer of most modern optimizers is an exponential moving average (EMA) of stochastic gradients with a single scalar decay, with a unified forgetting horizon along every direction in parameter space. Yet the per-sample gradient of any linear layer factorizes as a rank-1 outer product $g_t = \delta_t x_t^\top$, exposing the input activation as a natural $\textit{key}$ and the output-side error as a natural $\textit{value}$, which is the structure that EMA's flat matrix average discards. We propose $\textbf{DeltaMomentum}$, which interprets the buffer as an online linear associative memory of these key--value pairs and updates it via the classical delta rule. The resulting update is $\textit{anisotropic memory transport}$: directions queried frequently are forgotten quickly, directions queried rarely are preserved on long horizons, yielding an automatic, data-driven schedule matched to input statistics. We prove the buffer's expected fixed point is a Tikhonov-regularized Wiener predictor of the population gradient, which is equivalent to implicit input-side natural-gradient preconditioning at no covariance-inversion cost, and that the same mechanism strictly accelerates expected tracking-error contraction along every positive-density input direction under non-stationarity and reduces the per-direction iteration determinant in linear regression. DeltaMomentum is a drop-in replacement for the EMA accumulator in any base optimizer; we instantiate it as DeltaSGD and DeltaAdamW. A $\mu$P derivation shows the delta coefficient is width-invariant, enabling zero-shot hyperparameter transfer; we verify this with a coordinate check across five widths. The per-block asymptotic FLOP overhead is $\approx 15.74$% at zero persistent-memory cost (down to $7.3$% and $11.0$% realized at 67M/370M). On FineWeb-Edu, DeltaAdamW reaches AdamW's terminal validation loss in up to $31.35$% fewer steps at 67M and $19.28$% fewer steps at 370M. On CIFAR-10, DeltaSGD shows the same pattern against SGD-momentum, confirming the gain is not specific to Adam. Mechanistic diagnostics confirm that improvements in gradient-estimator quality, function-space prediction error, and input-feature conditioning are operative throughout training.

Exemplar-based image editing applies a transformation defined by a source-target image pair to a new query image. Existing methods rely on a pair-of-pairs supervision paradigm, requiring two image pairs sharing the same edit semantics to learn the target transformation. This constraint makes training data difficult to curate at scale and limits generalization across diverse edit types. We propose Delta-Adapter, a method that learns transferable editing semantics under single-pair supervision, requiring no textual guidance. Rather than directly exposing the exemplar pair to the model, we leverage a pre-trained vision encoder to extract a semantic delta that encodes the visual transformation between the two images. This semantic delta is injected into a pre-trained image editing model via a Perceiver-based adapter. Since the target image is never directly visible to the model, it can serve as the prediction target, enabling single-pair supervision without requiring additional exemplar pairs. This formulation allows us to leverage existing large-scale editing datasets for training. To further promote faithful transformation transfer, we introduce a semantic delta consistency loss that aligns the semantic change of the generated output with the ground-truth semantic delta extracted from the exemplar pair. Extensive experiments demonstrate that Delta-Adapter consistently improves both editing accuracy and content consistency over four strong baselines on seen editing tasks, while also generalizing more effectively to unseen editing tasks. Code will be made publicly available.

Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under the learner's policy. The core difficulty is not surprising data per se, but \emph{negative learning from surprising data}. High-surprisal failures can dominate finite-batch updates through large perpendicular components, while high-surprisal successes reveal opportunities the current policy would otherwise miss. The \textit{Delightful Policy Gradient} (DG) separates these cases by gating each update with delight, the product of advantage and surprisal, suppressing rare failures and preserving rare successes without behavior probabilities. In a tabular analysis, DG suppresses the perpendicular second moment of high-surprisal failures by a policy-overlap factor that vanishes as the learner improves. The advantage sign is essential for surprisal-based filtering: any learner-probability-only gate that suppresses rare failures also suppresses rare successes. On MNIST with simulated staleness, DG without off-policy correction outperforms importance-weighted PG with exact behavior probabilities. On a transformer sequence task with staleness, actor bugs, reward corruption, and rare discovery, DG often achieves nearly order-of-magnitude lower error. When all four frictions act simultaneously, its sample-efficiency advantage is order-of-magnitude and grows with task complexity.

Proteolysis-targeting chimeras (PROTACs) induce protein degradation through coordinated interactions among a degrader molecule, a target protein, and an E3 ubiquitin ligase. Yet computational prediction is often framed as if degradation were an intrinsic property of the degrader alone, overlooking the tuple-level context that determines activity. This mismatch is especially consequential in public PROTAC datasets, where degradation labels are sparse but molecule–target–E3 records are abundant. We introduce DegradeQuery, a tuple-conditioned framework that uses unlabeled records as structured relational evidence rather than incomplete labeled examples. DegradeQuery first performs counterfactual tuple pretraining, learning to distinguish observed molecule–target–E3 tuples from alternatives generated by replacing the target, the E3 ligase, or both. This objective induces a conditional compatibility representation before degradation labels are used, enabling the model to capture how degrader activity depends on biological context. The pretrained representation is then fine-tuned for high/low degradation prediction. On the official PROTAC-8K benchmark, DegradeQuery achieves 0.9065 AUROC and 0.8500 accuracy, outperforming reported semi-supervised results without pseudo-labeling, teacher models, distillation, or ensembles. Ablations, scaffold holdout, target–E3 holdout, and target-wise few-shot adaptation further support PROTAC degradation prediction as a tuple-conditioned rather than molecule-only problem.

Depth super-resolution (DSR) aims to recover a high-resolution (HR) depth map from its low-resolution (LR) counterpart. With color image guidance, this task is typically formulated as learning the residual between HR and LR in a low-dimensional feature space. However, this additive formulation is insufficient to accurately capture the complex relationship between HR and LR, especially under spatially varying degradations. In this paper, we introduce \textbf{DegBins}, a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling. Specifically, DegBins reformulates the regression-based DSR as a hybrid classification-regression problem, where the residual depth is represented as a linear combination of discrete depth bins weighted by their learned probability distribution, yielding more flexible and expressive representations. Furthermore, DegBins models the degradation relationship between HR and LR in a high-dimensional feature space, enabling adaptive bin range adjustment and probability optimization conditioned on local degradation characteristics. To progressively improve reconstruction quality, DegBins adopts a multi-stage refinement scheme, where each stage performs finer-grained bin partitioning and probability updating based on the former estimation. This coarse-to-fine design facilitates more accurate depth recovery, particularly in regions with severe degradations or complex structural variations. Extensive experiments across five benchmarks demonstrate that DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.

Imitation learning has achieved remarkable progress in robot manipulation, but its success heavily depends on large-scale demonstration data that are costly to collect. Recent work has therefore explored demonstration augmentation, but they are fundamentally limited in deformable manipulation, where task-relevant object variation is governed by high-dimensional deformations and physics-induced internal constraints rather than low-dimensional pose changes. We present **DeformGen**, a dynamics-based augmentation framework that achieves *topological diversity* for deformable objects. Instead of perturbing object pose, DeformGen expands the valid state distribution by applying localized physical disturbances, forward-simulating the dynamics, and stabilizing the result to obtain topology-coherent deformable states with physical plausibility. Given these synthesized states, DeformGen further transfers source manipulation trajectories via deformation-field warping, which lifts per-particle displacements into a continuous spatial function to adapt the end-effector trajectory consistently with the deformed geometry. In this way, our method augments both the state distribution and its associated manipulation behavior. Experiments on high-fidelity deformable manipulation benchmarks show that DeformGen consistently improves policy learning over training on the original demonstrations alone and over rigid-style augmentation baselines.

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. On held-out SCOPE-R test splits across Claude Code and OpenClaw backends, SkillSonar reduces attack success while preserving benign utility, maintaining modest token overhead, and transferring to OOD attack families. These results show that runtime guards can be skill-native, transparent, and evolvable policy artifacts for skill-augmented agents.

In recent years, AIGC technologies are capable of generating hyper-realistic forged facial images, posing severe threats to facial security safety. To tackle these challenges, early Deepfake research primarily centered on real-fake classification. Recently, growing efforts have been devoted to the Deepfake Attribution (DFA) of generated content. Nevertheless, existing research on Deepfake detection and attribution faces saturated performance in binary classification, limited diversity in datasets and algorithms, and imperfect evaluation protocols, which severely impede practical application. To address these limitations, we propose a comprehensive deepfake detection and attribution benchmark named DeepfakeGenome (DFG). It contains 100 facial forgery algorithms and 2M images in total, achieving 4× to 100× larger than prior DFA benchmarks. We further designed 4 protocols for practical evaluation, including a novel retrieval-based attribution paradigm. Unlike previous open-set evaluation metrics, the proposed retrieval metrics are more aligned with the real-world active defense situation of blacklist registration mechanisms. Based on these elaborate designs, we investigate the performance ceiling of deepfake attribution task. Over 2k+ experimental evaluations are conducted, and 10 insightful findings are derived. We hope this work can provide new insights into the DFA research field.

Recently, social choice theory has been found broadly useful for AI alignment and evaluation, often based on the axiomatic properties for combining preferences provided by social choice functions. However, for many sets of axioms, functions which $\textit{never}$ violate the axioms are known to not exist, e.g., Arrow's Impossibility Theorem. Recent work on learning novel rules to $\textit{minimize}$ axiom violations shows the effectiveness of machine learning but explores a limited class of axioms. In this work we show the effectiveness of standard social choice data structures as features for learning existing voting rules, resulting in networks that have better accuracy than past approaches while using an order of magnitude fewer parameters. Subsequently, we develop a process for $\textit{adding axiomatic properties}$ to existing voting rules. By building novel axiomatic loss functions we are able to use transfer learning to fine-tune existing voting rules in a way that quantitatively preserves their original behaviour while also exhibiting strong adherence to previously absent axiomatic properties, resulting in novel voting rules that are $\textit{closer}$ to the impossibility frontier than those in the machine learning or theoretical literature.

Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local instances. This is limiting because beat labels often depend on multi-beat rhythm context, including timing, compensatory pauses, and beat-to-beat morphological consistency. We present $\textbf{DeepArrhythmia}$, a tool-grounded multimodal framework for segment-contextualized beat-level ECG arrhythmia classification. Given a multi-beat ECG segment, DeepArrhythmia combines the raw ECG signal and a rendered waveform image, localizes R peaks to identify beat instances, and produces structured beat-level predictions. The framework decouples physiological measurement from evidence integration using specialized tools for beat localization, numerical rhythm--morphology extraction, and morphology-focused textual analysis. DeepArrhythmia uses segment-level confidence to route between minimal and rich evidence states, since richer physiological evidence is not uniformly useful. This agentic design integrates rhythm context, explicit physiological grounding, and selective evidence acquisition for decision making.

Symbolic library --- or Koopman dictionary --- selection is a fundamental challenge in data-driven dynamical systems. Extended Dynamic Mode Decomposition (EDMD), Sparse Identification of Nonlinear Dynamics (SINDy), and Kolmogorov--Arnold Networks for Dynamics (KANDy) all require the practitioner to commit to a function library at training time; Deep-Koopman Operators avoid this commitment but produce uninterpretable latent observables. We propose Deep-Koopman-KANDy, a structured approach to post-hoc symbolic dictionary readout that combines Deep-Koopman modeling with Kolmogorov-Arnold Networks for Dynamics (KANDy). The encoder and decoder of a Deep-Koopman Operator are replaced with two-layer Kolmogorov--Arnold Networks (KANs), and a level-set construction together with a chain-rule gradient identity exposes the compositional structure of the learned observables in a basis chosen \emph{after} training. We evaluate the method on the Lorenz system, the Chirikov standard map, the Ikeda map, and the Arnold cat map. On Lorenz it recovers the target dictionary $\{x,y,z,xy,xz\}$ with perfect recall and Jaccard score $0.79\pm0.06$; on the standard map it recovers a low-order Fourier basis matching the analytical structure; on Ikeda---which has no sparse polynomial representation---a misspecified polynomial readout still recovers the correct foliation coordinate $g\approx x^2+y^2$ together with a nontrivial outer function; and on the Arnold cat map --- used as a negative control because finite-dimensional Koopman closure is provably impossible --- the method fails to find a sparse closure, as expected.

Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but existing approaches treat them as given artifacts—either hand-crafted or prompt-generated—and often miss the task-specific, knowledge-intensive dimensions that matter most, distorting the reward signal. Our key observation is that *rubric construction is itself a research problem*: identifying what makes a response correct or insightful requires discovering and synthesizing external knowledge. We propose **Deep Research as Rubric (DR-rubric-8B)**, a two-stage framework for constructing such rubrics. Stage I elicits domain facts, structural constraints, and failure modes through iterative multi-turn agentic search; Stage II distills this evidence into atomic, independently verifiable constraints for GRPO-based policy optimization. Because the model under training can serve as its own rubric generator, DR-rubric-8B supports *bootstrap rubric generation* without frontier-model assistance. We evaluate on 6 benchmarks spanning agentic research and expert reasoning. Experiments show that DR-Rubric achieves strong competitive performance with only 1K–3K training instances, where GPT-5-generated rubrics particularly benefit breadth coverage on agentic tasks, while bootstrap rubrics exhibit a specialization-to-rebalancing evolution and achieve the best overall performance at the third iteration. Results demonstrate that reframing rubric construction from static evaluation templates into an evidence-driven research process yields more scalable, fine-grained reward signals for open-ended tasks.

Humans solve complex problems by flexibly shifting among reasoning modes, often without explicit deliberation: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance through fixed inference patterns. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across smaller, more controlled reasoning threads while preserving dependencies among subproblems. We evaluate DOLORES against state-of-the-art scaffolding methods across four hard benchmarks: grounded multi-hop reasoning, synthetic long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across four benchmarks, three model sizes, and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average, including methods tailored to individual benchmark families. Trace and token analyses suggest that while baseline scaffolds fail by overloading individual LLM calls, DOLORES succeeds by distributing cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucination. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time.

Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameterization. A probe family intended to reveal structure already present in a representation should therefore be stable under the relevant representation symmetries rather than be tied to a particular basis. We study this group action in the tractable exact setting of the final readout layer, where equivalent realizations induce affine changes of hidden coordinates. The resulting symmetry principle singles out a unique hierarchy of shallow coordinate-stable probes, with linear probes as its degree-1 member. We also show that a natural object for cross-model probe transfer is a shared probe-visible quotient--the representation modulo directions invisible to the probe family--rather than the full hidden state. Experiments on synthetic and real-world tasks support both predictions, showing where degree-2 probes help beyond linear ones and how quotient-based transfer enables coverage-aware monitor portability across model families. These results point toward a broader geometric representation theory of neural probing, with coverage-aware monitor transfer as a concrete operational consequence.

Turbulence is ubiquitous in engineering, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equations provide computational savings exceeding ten orders of magnitude but introduce unclosed terms requiring modelling (the closure problem). Existing machine-learning (ML) closures suffer distribution shift when trained offline on high-fidelity data, and ML models that bypass the governing equations often have limited capability to generalise. We develop a physics-derived deep learning closure for RANS, the Deep Algebraic Reynolds Stress Model (DARSM), which can be trained on one or two flow cases and generalise across an order of magnitude in Reynolds number, to unseen geometries, and across flow regimes. A neural network maps flow invariants to empirical parameters in an implicit algebraic Reynolds stress equation, derived from the Reynolds stress transport equations under the weak-equilibrium assumption, imposing significant physics-based structure on the ML closure. End-to-end optimisation through the governing PDEs and the coupled implicit closure eliminates distribution shift, but both unrolled and implicit automatic differentiation fail on the stiff coupled solver. We derive adjoint equations that exploit the solver's implicit-explicit structure to enable computationally efficient optimisation. On the canonical square-duct and periodic-hill benchmarks, DARSM reduces test velocity error as compared to the baseline RANS by $2$-$4\times$ across Reynolds number, geometries, and flow regimes, with peak case-level reductions of $12\times$. The model trained on attached, anisotropy-dominated flows (square duct) accurately generalises without retraining to separated flows (periodic hills), a regime change in the underlying turbulence physics. DARSM also outperforms five established ML methods: offline training, tensor-basis neural networks, field-inversion machine learning, DeepONets, and physics-informed neural networks.

Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks. In heteroskedastic regression, where the uncertainty of the target depends on the input, a common approach is to train a neural network that parametrises the mean and the variance of the predictive distribution. Yet to this day, training deep heteroskedastic regression models poses severe practical challenges in the trade-off between uncertainty quantification and mean prediction, such as variance overfitting, optimization difficulties and representation collapse. In this work, we identify the core issues and propose a simple and efficient procedure that addresses these jointly by post-hoc fitting a variance model across the intermediate layers of a pretrained network on a hold-out dataset. We demonstrate that this method is competitive with end-to-end trained mean-variance networks in heteroskedastic UQ on several data modalities. The method retains mean prediction accuracy, is cheap at both train and prediction time, and requires no additional data compared to existing methods. Finally, we show this method works on large scale foundation models for chemistry, paving the way for cheap heteroskedastic UQ in large scale neural networks without having to retrain such models end-to-end.

Many real world processes can be represented as compositions of functions along a Directed Acyclic Graph (DAG). In causal modelling these correspond to the underlying mechanisms, in engineering to the multiple fidelities present, and in gene-regulatory networks to the transcription factors. These functions are partially observed across the DAG, with noisy and heterogeneously sampled measurements, posing significant challenges for reconstruction, uncertainty propagation, and inference. To tackle these we place priors over functions and naturally arrive at Deep Gaussian Processes over DAGs. We theoretically study their prior-collapse behaviour, and the effect of graph topology and intermediate observations on the preservation of information. We obtain almost-sure lower bounds on the asymptotic frequency of depths at which distinction between inputs is preserved, identify broad kernel classes for which these hold, and prove an observation by \citep{dunlop2018} on the role of input connections. We offer a structured variational approximation that retains graph dependencies, satisfies compositional uncertainty, and captures the explaining-away behaviour of colliders. Finally, we empirically validate our theoretical results and our methodology, and model a latent-collider DAG, a protein signalling network, and a multi-fidelity heavy-ion collision task, attaining state-of-the-art performance while recovering the low-fidelity contributions and yielding explainability over the simulator hierarchy.