NeurIPS 2026 论文列表

Process reward models (PRMs) dramatically outperform outcome reward models (ORMs) for math reasoning and agent tasks, yet provide no benefit for chat and QA. No theory explains why, and practitioners choose between them by expensive trial and error. We introduce state-lift, a diagnostic that predicts whether a PRM is worth training for a new domain — in minutes, from ~500 labeled steps, before committing to expensive reward model training. State-lift measures how much step quality depends on trajectory state versus action text alone, and an accompanying effective gap distinguishes two regimes: state-noise-dominant (PRM essential) and action-gap-dominant (ORM sufficient). Across ten domains and eleven published PRM-ORM comparisons, state-lift correctly predicts PRM advantage, and a minutes-scale linear estimate matches the outcome of full Llama-3.1-8B reward model training — including CaSiNo negotiation (+0.055 lift at SL = 0.22). The accompanying two-branch decision protocol turns state-lift into an actionable PRM-vs-ORM workflow that runs in minutes on a single CPU.

Low-altitude economy has been experiencing rapid growth in recent years, with significant contributions to the global economy. While common drone tasks such as delivery, inspection, and search-and-rescue typically use Global Navigation Satellite Systems (GNSS) to navigate, there is an increasing need for developing alternative solutions as GNSS signals can be easily jammed, spoofed, or unavailable over a prolonged operational time. As such, cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a potent alternative that lets an autonomous drone localize itself when GNSS fails. Despite strong recent progress, three limitations persist in current CVGL methods: 1) global-descriptor designs compress the patch grid into a single vector without separating what is shared across the view gap (layout) from what is not (texture); 2) altitude-related scale variation is implicitly retained in the learned embedding rather than treated as a nuisance to be marginalized out; and 3) multi-objective training relies on hand-tuned scalars over losses that live on incompatible gradient scales. To address these limitations, we propose SkyPart, a lightweight swappable head for patch-based vision transformers (ViTs) that institutes explicit part grouping over the patch grid. SkyPart has four components grounded in established theory: (i) learnable prototypes that compete for patch tokens via a single-pass cosine assignment; (ii) altitude-conditioned linear modulation applied only during training so that the retrieval embedding is altitude-free at inference; (iii) a graph-attention readout over active prototypes; and (iv) a Kendall uncertainty-weighted multi-objective loss whose stationary points are Pareto-stationary. At 26.95M parameters and 22.14 GFLOPs, SkyPart is the smallest among the top-performing methods in our comparison and sets a new state of the art on SUES-200, University-1652, and DenseUAV datasets under a single-pass, no-re-ranking, no test-time augmentation (TTA) protocol. Furthermore, its accuracy gap to the strongest baseline widens under the ten-condition WeatherPrompt corruption benchmark

Double Oracle (DO) and PSRO approximate Nash equilibria in two-player zero-sum games by iteratively expanding a strategy population with best responses. Online Double Oracle (ODO) interleaves multiplicative weights updates (MWU) with discovery and obtains an $O(\sqrt{k \ln k / T})$ rate. We identify the \emph{reinitialisation} step as an underexplored design choice: at each expansion, MWU-based methods reset newly discovered strategies to a uniform prior. We introduce Virtual Double Oracle (VDO), which exploits a bilinear identity---a strategy's full hindsight loss history collapses to its utility against the time-averaged opponent---to initialise each new strategy with the MWU state it would have had from the start. Conditional on the discovered population, VDO recovers the fixed-population rate $O(\sqrt{\ln k / T})$ asymptotically, removing ODO's leading-order $\sqrt{k}$ window-decomposition penalty. Discounted VDO adds a single parameter $\beta$ to control finite-horizon prior strength. Experiments across matrix games, poker, and Goofspiel validate both contributions: pure VDO confirms the asymptotic rate, and discounted VDO gives the strongest finite-horizon performance.

We show that a generative model can discover concepts from data in an unsupervised setting while learning to generate. The Dirichlet Concept Diffusion Model (DCDM) embeds concept discovery into diffusion-based generation. DCDM learns concept centers and infers a Dirichlet distribution over them for each input. The resulting weighted center shapes the forward diffusion mean and reverse denoising process, so components are learned through the same evidence lower bound used to model the data. The method uses no class labels, attribute annotations, captions, pretrained text-to-image priors, or semantic concept supervision. Analysis shows how the formulation preserves concept-level information along diffusion paths and reduces denoising ambiguity, creating pressure for concept centers to capture stable modes. Experiments across diverse image domains show that the learned components form coherent prototypes, support interventions, and reflect recurring visual structure.

Flexible molecular docking is crucial for drug discovery; however, existing flow-matching generative models often produce physically invalid conformations (e.g., steric clashes, distorted bond geometry). Our analysis suggests that a primary contributor to this challenge lies at the modeling level: when the flow is parameterized by standard equivariant networks, an intrinsic approximation floor can emerge, potentially hindering the learned velocity field from reaching its optimal convergence bound, particularly for highly flexible molecules. We present UniFlowDock, which addresses this by introducing strictly Complete Equivariant Velocity Fields, thereby eliminating the dimensional incompleteness of standard architectures. This theoretical completeness is further bolstered by Fragment-Adaptive Optimal Coupling, a method that structurally linearizes transport trajectories and decomposes the generation process into physics-aware subproblems. Experiments on PDBBind and PoseBusters demonstrate UniFlowDock achieves state-of-the-art accuracy and physical validity, showing consistent gains in highly flexible docking scenarios where target distributions exhibit higher transport complexity.

How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of ESMFold, OpenFold, and Boltz-1. Across all three models, we find a shared two-stage computational structure. In the first stage, early blocks initialize *pairwise biochemical signals*: features like charge propagate from sequence into pairwise representations through architecture-specific pathways. In the second stage, late blocks develop *pairwise spatial features*: distance and contact information accumulate in the pairwise representation. We verify these mechanisms causally by showing that steering charge and distance features induces predictable structural changes. Furthermore, these representations are functionally interchangeable: pairwise states can be linearly aligned and substituted across models. Together, these results suggest that folding trunks with different architectures, inputs, and training procedures converge on a shared representational organization for mapping sequence chemistry into spatial geometry.

Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particularly insidious: reliable assessment of synthetic plans is time-consuming, with automatic methods lacking. In this work, we present RetroTrim, a retrosynthesis system that successfully avoids nonsensical plans on a set of challenging drug-like targets. Compared to common baselines in the field, our system is not only the sole method that succeeds in filtering out hallucinated reactions, but it also results in the highest number of high-quality paths overall. The key insight behind RetroTrim is the combination of diverse reaction scoring strategies, based on machine learning models and existing chemical databases. We show that our scoring strategies capture different classes of hallucinations by analyzing them on a dataset of labeled retrosynthetic intermediates. To measure the performance of retrosynthesis systems, we propose a novel evaluation protocol for reactions and synthetic paths based on a structured review by expert chemists. Using this protocol, we compare systems on a set of 32 novel targets, curated to reflect recent trends in drug structures. While the insights behind our methodology are broadly applicable to retrosynthesis, our focus is on targets in the drug-like domain. By releasing our benchmark targets and the details of our evaluation protocol, we hope to inspire further research into reliable retrosynthesis.

Clinical drug development is high stakes. Small statistical errors propagate into trial design, participant exposure, and stop/advance decisions. As agents are increasingly used to support analysis and decision-making, more robust evaluations of their capabilities in clinical domains are needed. We introduce TrialAgentBench, a public benchmark in which agents must analyse participant-level evidence, choose defensible estimands and methods, quantify uncertainty, diagnose assumption failures, and carry those analysis decisions into downstream drug-development decisions. TrialEvalBench contains 400 patient-level analysis tasks across design, assumption, and context tiers. TrialDevBench contains 20 sequential development programmes across five scenario worlds, each starting from a confounded 10,000-patient observational extract and proceeding through asset nomination, endpoint and sample-size design, deterministic phase trials, phase analysis, and stop/advance decisions. The release spans 420 evaluated tasks or programmes, 528,660 simulated subjects, 77.6 million public tabular records, and 1.46 billion row-variable cells. Agents see only participant-facing data; grader-only files contain cell-appropriate targets, deterministic phase state, and scoring code. On TrialEvalBench, GPT-5.4 completes all 400 items but matches the required estimand/method class (e.g., log-HR versus RMST or risk-difference targets) for only 215/400 and produces an acceptable next-trial sample-size plan for 161/400. On TrialDevBench, GPT-5.4 and Claude Opus 4.7 complete all 60 seeded development programme runs per model, yet frequently nominate the wrong initial asset under confounding and choose evidence-supported stop/advance timing in fewer than one-third of programmes. Together, the two suites make clinical-trial decision quality measurable. Current agents can effectively execute familiar analyses, but fail to make the decisions those analyses exist to support.

Flow matching has shown strong potential in generative tasks, while its optimization via Reinforcement Learning (RL) remains underexplored, especially in continuous-discrete mixed settings. Moreover, flow matching is formulated as an Ordinary Differential Equation (ODE), whose deterministic trajectories do not naturally support RL optimization. Introducing stochasticity by converting the entire trajectory into a Stochastic Differential Equation (SDE) is a common practice. Nevertheless, not all timesteps contribute to the final outcomes, and redundant exploration introduces additional noise. Furthermore, in multi-objective settings, some objectives may dominate the optimization while others receive insufficient updates. In this study, we propose an RL-guided continuous-discrete flow matching framework with temporal selective exploration for 3D de novo molecular design. Specifically, our method jointly optimizes continuous and discrete flow matching for atomic coordinates and molecular identities, respectively, while restricting exploration to timesteps that primarily contribute to target properties, reducing ineffective exploration. We also introduce a reward-based advantage calibration mechanism to mitigate objective dominance in multi-objective optimization. The framework is applied to design inhibitors for both the well-studied target protein EGFR and the challenging Pin1 protein. We identify some novel candidate inhibitors, supported by in silico validation.

Protein optimization remains a longstanding goal in life sciences. Existing machine learning–assisted directed evolution (MLDE) methods primarily rely on sequence-only features, overlooking the critical spatial constraints and co-evolutionary interactions encoded in protein structures. However, directly integrating structural information remains challenging due to the scarcity of reliable mutant structures. To address these issues, we propose **StructEvo**, a novel structure-aware reinforcement learning framework for protein directed evolution. StructEvo employs a delta-structure fusion encoder to approximate mutant structure features via feature differences, enabling dynamic incorporation of spatial knowledge. The vast mutation space is then decomposed into manageable subspaces through a structure-aligned hierarchical action network, while a geometric constraint further stabilizes delta feature learning. Our approach outperforms prior state-of-the-art methods by 9.2% and 16.3% on two challenging optimization benchmarks, and further identifies an experimentally validated epistasis pattern in GFP, highlighting the importance of structural guidance for effective protein directed evolution.

Generative protein models are increasingly used for functional sequence design, yet the process by which biological information is organized during generation remains poorly understood. Diffusion protein language models provide a tractable setting for this question, as sequence generation proceeds through an explicit denoising trajectory from highly corrupted states to complete proteins. This trajectory enables a temporal view of interpretability: beyond identifying which biological signals are represented, it allows us to examine when these signals emerge and when specific residues become committed. Here, we analyze DPLM representations using sparse autoencoders trained across layers and noise levels. The resulting features capture biologically meaningful signals at both residue and protein scales, align with functional annotations, and preserve downstream biological information under reconstruction. Following these features along the denoising trajectory reveals a consistent functional ordering: catalytic-enriched features pre-activate at still-masked catalytic positions before residue identity is resolved, and catalytic residues are subsequently recovered earlier by the iterative denoiser. This prioritization remains significant after controlling for prediction difficulty, sequence context, amino-acid identity, structural environment, and evolutionary conservation, and is not reproduced by a random-feature null. Across ProteinGym deep-mutational-scanning assays, residues recovered earlier during denoising are also more mutation-sensitive. These results reveal a temporal organization of biological information in diffusion-based protein generation, in which functionally important residues are not only represented, but preferentially committed during sequence formation.

Behavior cloning (BC) in non-Markovian environments is a challenging problem because policies have to reason over contextual information over long horizons. Existing policy architectures rely on recurrent or attention-based mechanisms to capture long-term dependencies. However, recurrent models suffer from hidden-state collapse and gradient instability under backpropagation through time, while attention-based models are fundamentally limited by context length. To address these issues, we propose Keyframe Mnemonics, a novel self-supervised method that $\textit{discovers}$ a set of information-critical observations ($\textit{mnemonics}$) by learning an objective from randomly sampled past observations and using it as a reward for keyframe selection. We then train a BC policy that conditions on the discovered keyframes to model the action distribution. Under near-optimal keyframe selection, our formulation provides context retention guarantees over an infinite horizon, while maintaining a small set of decision-relevant keyframes in the policy's working memory. We evaluate our method on synthetic memory domains, where mnemonic-conditioned BC policies achieve $100$% success rates (SR) and generalize to horizons orders of magnitude beyond training without performance degradation. Additionally, we evaluate on memory intensive robot manipulation benchmarks, where we observe an absolute $15$-$30$% improvement in SR over strong memory-augmented baselines on $23$ tasks. Code and videos are available at https://keyframe-mnemonics.github.io.

Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informative. Existing reinforcement learning and off-policy generative approaches often degrade under surrogate noise, and position-agnostic mutation proposals risk disrupting functionally critical residues. We introduce SILO, a trajectory-level self-improvement imitation framework for oracle-budgeted protein design. SILO uses a hierarchical edit policy that decomposes each mutation into a position choice followed by a residue choice. In each active-learning round, the policy samples candidate trajectories via incremental stochastic beam search without replacement (SBS), and a UCB-based proxy ensemble, combined with an alanine-scan fitness score (AFS), selects candidates with functionally relevant edits for in silico oracle evaluation. The policy is then updated by next-action cross-entropy imitation on the round’s best oracle-labeled trajectories, avoiding value-function estimation. Across eight reproduced protein fitness landscapes and five strong baselines from prior work, SILO achieves the highest maximum and top-100 mean fitness on 8 of 8 landscapes within our evaluations, often exhibiting faster early-stage improvement. In low-data and noisy-proxy stress tests on two landscapes per setting, SILO remains competitive or best when several baselines degrade. Ablations show that SBS with AFS account for much of the gains, with iterative imitation providing additional improvement.

Generalized category discovery (GCD) becomes substantially more challenging when the number of novel classes is unknown. We argue that, after the backbone is fixed, this stage should be treated as seen-constrained model-order selection rather than as an auxiliary clustering detail. The selector must estimate the class count without novel labels while remaining consistent with the labeled seen categories available in the standard GCD setting. We instantiate this view by constructing a nested merge path from a seen-constrained overclustering and selecting the coarsest near-optimal cut under observable surrogate decision risks. These risks combine seen-class consistency, cross-seed stability, unlabeled-side compactness, and a tiny-cluster degeneracy penalty. The resulting protocol separates class-count error, downstream clustering quality, and robustness. Where an aligned public unknown-$K$ baseline is available, namely on SelEx, the selector reduces class-count error on all four fine-grained datasets, including a reduction from 342 to 15 classes on Herbarium-19. Broader-domain diagnostics further distinguish ImageNet100, where the default selector can underestimate the class count toward the seen-class regime, from CIFAR100, where the selector landscape exposes an accuracy-count operating-point trade-off. The mixed accuracy outcomes reveal distinct count-, path-, and representation-level bottlenecks, supporting unknown-$K$ selection as a decision layer that should be evaluated separately from representation learning.

Lipid Nanoparticles (LNPs) are widely used as delivery systems for nucleic acid therapeutics, where transfection efficiency is determined by both the identities of constituent lipid components and their composition ratios. While prior studies have focused on learning molecular representations for ionizable lipids, modeling how multiple components and their ratios jointly influence LNP performance remains underexplored. In this work, we propose STRATA, a framework that models molecule interaction between LNP components, which is known to contribute to LNP transfection efficiency. Our approach is built on two complementary views: (1) a ratio-centric view that captures interaction patterns induced by composition ratios through a transformer with a Ratio-induced Positional Embedding, and (2) a molecule-centric view that incorporates interaction-induced effects into structure-based molecule embeddings. By jointly training and aligning these views, our model integrates molecular structure and composition ratio within a unified framework that captures interaction-driven effects. Experiments demonstrate that our method improves prediction accuracy and generalization to unseen molecules and ratios, highlighting the effectiveness of our approach.

Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because the large search space makes combinatorial screens prohibitively expensive, time consuming, and often technically infeasible. Predictive models can fill this gap, yet existing methods typically require molecular profiling of each sample and per-cohort training, limiting their applicability when time and tissue are scarce. To address this challenge, we introduce ScreenShot, a hierarchical transformer pretrained on 40 drug screening datasets covering 3,700 drugs and 6,000 biological samples, whose architecture mirrors the nested structure of screening data. Given a few-shot context of observations from a new patient, ScreenShot predicts the response of the sample to combination therapies through in-context learning, operating directly on functional measurements with no fine-tuning and no molecular profiling. On four held-out datasets, ScreenShot outperforms all baselines in both prediction accuracy and identification of selectively effective treatments. ScreenShot's internal representations are directly useful for experimental design: we use them to drive a weighted $k$-means++ active learning strategy that selects which experiments to run, achieving the same hit detection as uniform screening with a third of the budget. Source code and interactive dashboard: https://github.com/AnonymousAccount3/screenshot

Sparse autoencoders (SAEs) are a central tool in mechanistic interpretability. However, existing SAEs are primarily trained per layer. The modeling subspace is therefore fixed by layer identity, independent of which token-layer states actually drive each prediction. We argue that this constraint contributes to several limitations observed in layer-wise SAEs, including low feature utilization, high dictionary redundancy, and features that lack direct behavioral grounding. In this paper, we propose ScopeSAE, which selects the modeling subspace per token by attributing each prediction to its most influential token-layer state via normalized gradient-based attribution, and learns features over the resulting prediction-relevant subspace. Empirically, ScopeSAE yields an effect we term reconstruction-better-than-original. Written-back reconstructions of the SAE produce lower next-token cross-entropy than the original activations, an outcome that, to our knowledge, has not previously been reported for SAEs and that inverts the usual reconstruction-fidelity trade-off. Through interventional analyses and a KL fine-tuning counter-experiment, we show that this effect is attributable to ScopeSAE's prediction-relevant subspace itself rather than to architectural changes. ScopeSAE further improves effective feature count, interpretability, utilization, and dictionary redundancy over existing layer-based baselines, suggesting that choosing the SAE modeling subspace by predictive relevance leads to more useful and behaviorally meaningful features.

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents’ capability in driving this process, we present **SciResearchBench** (Scientific - Research - Bench), a dedicated benchmark for autonomous scientific literature discovery. SciResearchBench consists of two complementary task types: (1) **Deep Research**, which requires tracking down a specific target paper through a progressive, multi-step probing process, and (2) **Wide Research**, which requires comprehensively collecting a set of papers satisfying given conditions. Compared to previous benchmarks on agentic web browsing, SciResearchBench is distinguished along three dimensions: it is **research-oriented**, calling for in-depth comprehension of scientific concepts; **literature-focused**, demanding fine-grained utilization of detailed information; and **open-ended**, involving an unknown number of qualified papers and thus requiring deliberate reasoning and search throughout. These properties make SciResearchBench uniquely suited for evaluating autonomous research capabilities, and extraordinarily challenging. Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research, while many other strong baselines fall below 5%.

We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graph-structured data. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design supports invalid logit masking for enforcing structural constraints, including chemical valence and ordering constraints, and enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive or state-of-the-art sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models.