NeurIPS 2026 Papers

Fairness impossibility results often look like distinct scalar incompatibility statements. We show that several share one RKHS geometry: fairness criteria are linear constraints on conditional mean embeddings, and unequal base rates make the law of total expectation overdetermine those constraints. This view yields four results. The Kleinberg--Mullainathan--Raghavan dichotomy needs only group-conditional unbiasedness, not full calibration. The \emph{Pok\'emon theorem} shows that a distinct group pair satisfying any finite collection of linear mean-fairness criteria leaves a residual violation witnessed by the MMD, decaying at the Kolmogorov $m$-width rate under spectral regularity. The same tools prove an impossibility for fair feature learning: parity and class-conditional separation in representation space force class collapse under unequal base rates. The approximate relaxations yield signal and error frontiers, allowing a trade-off between real-world estimators and fairness goals. Experiments on standard fairness benchmarks are consistent with our bounds.

AI tools are increasingly integrated into real-world workflows. However, existing measures of reliance on these tools focus on AI output adoption or on self-reported indicators, rather than how task effort is distributed between users and tools. Here, we introduce offloading score, a measure of reliance that quantifies the fraction of cognitive effort offloaded to an AI tool. Offloading score is simulation-based---we construct a counterfactual workflow by estimating how the user would have completed the task without the tool, and then computing the fraction of steps saved by using the tool. We validate offloading score through intrinsic evaluations of metric validity, and a controlled user study ($n=40$) with developers performing programming tasks using AI tools. We vary time pressure to test whether reliance measures capture the known increase in reliance under time pressure. We show that offloading score detects significantly higher reliance in time-constrained settings ($+43\%$, $p=0.018$), while usage-based and self-reported baseline measures do not distinguish the conditions. We complement this with descriptive insights showing that higher reliance manifests as greater delegation and more direct reuse of AI outputs. Finally, we demonstrate an approach of using offloading score in combination with target outcomes of reliance (e.g., task understanding) to identify when reliance may be (in)appropriate. Our framework offers two contributions: an instrument users can apply to measure and reflect on their own reliance, and a quantitative signal that agent designers can utilize to mitigate overreliance.

Understanding how neural activity encodes behavioral and sensory variables is a key challenge in systems neuroscience. This requires models that go beyond predicting activity from labels and instead support source-conditioned counterfactual editing: given a recorded source response, we should be able to edit one behavioral or stimulus variable and predict how neural activity would change while preserving other observed factors and source-specific variability not explained by the labels. Here, we introduce **Neural-DISCO**, a disentangled representation learning framework for counterfactual modeling of neural activity. Neural-DISCO partitions the latent space into label-specific components, each associated with an observed behavioral or stimulus variable, together with a residual latent that captures variability not supplied through observed labels. Across simulated and real neural recording datasets, we show that this structure enables selective manipulation of individual labels to generate counterfactual neural responses while preserving the remaining content of the original activity. Further, to gain insight into how behavioral and stimulus variables are encoded at single-neuron resolution, we pair this disentangled framework with feature attribution methods that identify which neurons are most important for each label. We find that disentanglement enhances the recovery of known functional cell roles in both synthetic and real data. Together, these results support Neural-DISCO as a framework for controlled counterfactual modeling of neural activity and provide a practical interface for probing how neural populations encode behavior and sensory information.

Reinforcement learning has rapidly become the dominant paradigm for training software engineering (SWE) agents on long-horizon, multi-turn tasks such as resolving real-world GitHub issues. Yet existing pipelines suffer from a fundamental credit-assignment bottleneck: rewards arrive only at the end of trajectories that may span dozens of file edits, shell commands, and test invocations, leaving every intermediate decision indistinguishable from luck. We observe that containerised SWE tasks provide a particularly useful form of environment forkability: a commit hash plus a container image specifies a real executable software state that can be restored cheaply and exactly, with auditable provenance and without a simulator-to-reality gap. We exploit this property by introducing Counterfactual Rollout Replay (CRR), a training-time procedure that re-executes the environment from selected decision points with alternative actions and assigns each selected step an advantage equal to the sampled on-policy versus counterfactual return differential. CRR requires no learned process reward model, no human rubric annotation, and no oracle hindsight signal; it is free of auxiliary process labels and reward-model training, while still incurring extra environment-replay compute. Applied to a 14B base model on SWE-Gym and evaluated on SWE-bench Verified and SWE-rebench, CRR-trained agents reach higher resolution rates with substantially fewer trajectories than outcome-only GRPO and complement orthogonal advances such as PRM-based scoring and trajectory search.

We study finite-horizon two-player zero-sum perfect-recall partial-information games and ask for the minimal finite-dimensional state sufficient to answer all rooted observation-measurable unilateral continuation queries. For each player $i$ and information set $I$, we consider the span $\mathcal L_i(I)$ of feasible counterfactual beliefs and the effective local query space $\mathcal E_i(I)$ generated by rooted continuation queries restricted to $\mathcal L_i(I)$. We prove that its dimension $d_i(I)$ is simultaneously the rank of the local counterfactual query operator, the minimum core-query basis size, the minimum exact local realization dimension, and the dimension of the canonical quotient $\mathcal L_i(I)/\mathcal N_i(I)$, yielding reduced counterfactual predictive-state representations, unique up to similarity, with exact first-return update operators. Aggregating the local ranks defines the deviation-conditioned predictive-state dimensions $d_t^i$, $d_t$, $d_\star$, and $D_\star$. We then prove that local rooted payoff-query control transfers to global exploitability, and under local design richness and bounded one-step parameter norms obtain a rollout-based upper bound in these minimal coordinates. We complement this with a minimax lower bound showing that $\Omega(d/\gamma^2)$ local rollouts are necessary even when the peak DCPSD equals $d$, and with an exponential separation theorem exhibiting games with $d_\star=m$ but observable continuation-trace complexity $2^m$. Finally, we show that DCPSD recovers finite-rank predictive-state, observable-equivalence, and linearly parameterized continuation-law models as special cases.

Estimating counterfactual outcomes when multiple treatments are applied simultaneously, the composite treatment setting, is fundamentally harder than the single-cause case: the treatment space grows combinatorially, most combinations are unobserved, and confounding is entangled across dimensions. We propose PACE (Progressive Alignment for Composite Effects), which exploits a known causal DAG over treatment variables to progressively transform the observational data distribution into the target interventional distribution. PACE performs K sequential augmentation steps in reverse topological order, each isolating a single treatment component and conditioning only on its parents in the DAG. We derive the closed-form optimal augmentation density minimizing KL divergence at each step, establish finite-sample bounds prescribing the augmentation budget via DAG-aware selection bias ratios, and show that the DAG provides a deterministic processing order that eliminates the need for random permutation averaging. On semi-synthetic benchmarks with real covariates (IHDP, Twins, Hillstrom) and controlled synthetic environments, PACE substantially outperforms seven baselines on both continuous and binary outcomes, with the largest gains on rare treatment combinations where confounding is most severe. Ablations confirm consistent improvements over the closest prior method across varying DAG topologies, confounding strengths, and under DAG misspecification.

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple high-quality explanations that (1) affect only a small portion of the features, (2) can be applied to tabular data with heterogeneous features, and (3) are consistent with the user-defined constraints. We proposeCounterFlowNet, a generative approach that formulates CF generation as sequential feature modification using conditional Generative Flow Networks (GFlowNet). CounterFlowNet is trained to sample CFs proportionally to a user-specified reward function that can encode key CF desiderata: validity, sparsity, proximity and plausibility, encouraging high-quality explanations. The sequential formulation yields highly sparse edits, while a unified action space seamlessly supports continuous and categorical features. Moreover, actionability constraints, such as immutability and monotonicity of features, can be enforced at inference time via action masking, without retraining. Experiments on eight datasets under two evaluation protocols demonstrate that CounterFlowNet achieves superior trade-offs between validity, sparsity, plausibility, and diversity with full satisfaction of the given constraints.

Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may be common, yet the caption may describe the wrong relation in the image. Many evaluations intended to test this behavior can be solved without checking the pairing at all, because negatives differ in caption style, template, length, object frequency, or image statistics. We propose counterfactual pairing cycles, a blocked evaluation primitive that reuses the same two images and the same two captions on both sides of the comparison, changing only which image is paired with which caption. This makes image-only, text-only, and additive component shortcuts cancel exactly in finite samples. The same contrast also gives a training loss for relational outlier exposure and a diagnostic for bilinear vision-language scores. Across synthetic controls, GQA, and COCO, cycles separate coarse image-caption matching from stricter role-binding failures. In a shortcut-contaminated COCO outlier-exposure stress test, a model selected by a perfect shortcut validation AUROC transfers poorly to exact relational cycles, while cycle training improves CycleAcc from \(0.576\) to \(0.911\). The main lesson is simple: to test whether a model understands a pairing, the benchmark should keep the parts fixed, change the pairing, and ask only about coupling.

We study stochastic linear bandits under a natural combination of batching and communication constraints: the time horizon is partitioned into batches of equal size $B$, and during each batch the learner sends $B$ requested arm pulls to an agent, who then observes the corresponding $B$ rewards and responds with a single bit of feedback to the learner. For each batch, the learner specifies the 1-bit quantization rule the agent uses, which may depend on all previously received bits but not on any past rewards directly. This setting addresses a significant yet unexplored ``middle ground'' between previous models having per-round quantization only $\textit{or}$ total bit budgets only. We establish a minimax lower bound showing that $\Omega(B\min \lbrace d,\log\lvert \mathcal{A} \rvert \rbrace)$ regret is unavoidable due to the 1‑bit communication bottleneck, even in the absence of noise. Combined with standard statistical limits, this yields a general lower bound of $\widetilde{\Omega}(B\min\lbrace d,\log\lvert \mathcal{A} \rvert \rbrace + \sqrt{dT \min \lbrace d,\log\lvert \mathcal{A} \rvert\rbrace })$. We develop two phased‑elimination algorithms based on $G$-optimal designs and 1‑bit mean estimation. The first achieves $\widetilde{O}(dB + d\sqrt{T})$ regret, matching the lower bound up to logarithmic factors when $\lvert \mathcal{A} \rvert = \exp(\Omega(d))$, and the second incorporates a safe‑arm identification and warm‑start procedure to obtain $\widetilde{O}(B\log\lvert \mathcal{A} \rvert + d^{3/2}\sqrt{B} + \sqrt{dT\log\lvert \mathcal{A} \rvert})$ regret, which is near‑optimal in broad scaling regimes of $(\lvert \mathcal{A} \rvert, B, d,T)$. Together, our results demonstrate that a single bit of feedback per batch suffices to preserve nearly order‑optimal regret across a wide range of settings, even in the case of large batch sizes such as $\Theta(\sqrt{T})$.