NeurIPS 2026 论文列表

Large Language Models (LLMs) increasingly ship with “thinking modes”, yet their counterpart, the “no-thinking” has received far less exploration. In this work, we revisit language model “no-thinking” behavior along the following efforts: **(a) Explore the definition of no-thinking.** Rather than relying on proxies like thinking-mode control, we split each response into pre-answer text and a final answer, scoring both answer-only compliance and the question–pre-answer relevance. **(b) Broad experimental coverage.** We evaluate multiple no-think controls (thinking-mode toggles, prompt instructions, *etc.*) across boolean, multiple-choice, and open-ended tasks, on open-source models with scaled variants, and proprietary models. With extensive experiments, we found that **(i)** Explicit no-think controls do not reliably eliminate visible reasoning-like content. Instead, models exhibit **(ii)** *“thinking inertia”*: residual content is systematically organized by the task's answer space, with boolean verification compressing most easily, multiple-choice tasks forming an intermediate regime, and open-ended tasks remaining the most resistant. **(iii)** We further identify what we call a no-thinking and performance trade-off in open-ended: stronger answer-only constraints on complex tasks either fail to suppress the intermediate payload or succeed by removing computation needed for accuracy. **(iv)** Finally, we show that compressibility depends strongly on the structural support provided by the question itself. Thus, no-think controls are not direct guarantees of no-thinking; they must be evaluated jointly through answer-only success, visible payload, and task accuracy. We hope our work moves LLMs closer to a human-like ability to stop thinking on demand.

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, **AutoTTS**, that changes what researchers design: from individual TTS heuristics to environments where TTS strategies can be discovered automatically. The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. As a concrete instantiation, we formulate width--depth TTS as controller synthesis over pre-collected reasoning trajectories and probe signals, where controllers decide when to branch, continue, probe, prune, or stop and can be evaluated cheaply without repeated LLM calls. We further introduce beta parameterization to reduce search-set overfitting and fine-grained execution trace feedback to improve discovery efficiency by helping the agent diagnose why a TTS program fails. Experiments on mathematical reasoning benchmarks show that the discovered strategies improve the overall accuracy--cost tradeoff over strong manually designed baselines. The discovered strategies generalize to held-out benchmarks and model scales, while the entire discovery costs only **$39.9** and **160 minutes**.

Advances in large language models (LLMs) have created new opportunities in data science, but their deployment is often limited by the challenge of finding relevant data in large data lakes. Existing methods struggle with this: both single- and multi-agent systems are quickly overwhelmed by large, heterogeneous files, and master–slave multi-agent systems rely on a rigid central controller that requires precise knowledge of each sub-agent’s capabilities, which is not possible in large-scale settings where the main agent lacks full observability over sub-agents’ knowledge and competencies. We propose a novel multi-agent paradigm inspired by the blackboard architecture for traditional AI models. In our framework, a central agent posts requests to a shared blackboard, and autonomous subordinate agents--either responsible for a partition of the data lake or retrieval from web--volunteer to respond based on their capabilities. This design improves scalability and flexibility by removing the need for a central coordinator to know each agent’s expertise or internal knowledge. We evaluate the approach on three benchmarks that require data discovery: KramaBench and modified versions of DSBench and DA-Code. Results show that the blackboard architecture substantially outperforms strong baselines, achieving 13%–57% relative improvements in end-to-end success and up to a 9% relative gain in data discovery F1 over the best baseline.

Scientific discovery is a closed-loop process in which hypotheses guide data acquisition, and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locally but fail to generalize. Thus, the key challenge is selecting informative observations to resolve uncertainty, shifting the focus from static inference to adaptive data acquisition. To address this, we propose LLM-AutoSciLab, a closed-loop framework that couples hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. Rather than fitting models to passively collected data, LLM-AutoSciLab iteratively proposes plausible hypotheses, selects informative experiments to distinguish among them or refine them, and updates its state based on the resulting evidence. To evaluate dynamic, closed-loop scientific discovery with active data acquisition, we introduce ActiveSciBench-Chem (57 enzyme-kinetics domains) and ActiveSciBench-GRN (45 gene-regulatory-network tasks), benchmarks that model discovery as a budget-constrained process requiring adaptive experiment design, variable selection, and recovery of true mechanisms. Across NewtonBench, ActiveSciBench-Chem, and ActiveSciBench-GRN, LLM-AutoSciLab outperforms prior methods, achieving 67.6% and 35.1% symbolic accuracy and 31.1% exact graph recovery, respectively. Moreover, hypothesis-guided experimentation is 2x--5x more sample-efficient than the strongest competing baselines.

The commercialization of LLM applications is the next frontier in online advertising, with *LLM-native advertising* emerging as a promising paradigm by integrating ads into LLM-generated content. However, classic mechanisms are no longer applicable in this setting where the auction object is shifted from discrete ad slots to distributions over LLM outputs, and existing methods are impractical in industrial scenarios due to ignored externalities or high inference costs. To address these issues, we propose LLM-Auction, the *first* learning-based generative auction mechanism that *integrates* auction and generation. By formulating the allocation as preference alignment between LLM outputs and a mechanism objective that balances advertiser value and user experience, we optimize the LLMs to inherently model allocation externalities without extra inference cost. Theoretically, we identify the allocation monotonicity and continuity of LLM-Auction, and prove that a simple first-price payment rule exhibits favorable incentive properties. Furthermore, we build an LLM-as-a-judge simulation environment for quantitative evaluation, and experiments demonstrate that LLM-Auction achieves the state-of-the-art allocation efficiency while satisfying key mechanism properties.

Recovering governing Ordinary Differential Equations (ODEs) from data is a central challenge in modeling dynamical systems across scientific domains. Existing approaches cast discovery as a static inference problem over fixed datasets, implicitly assuming that the observed trajectories are sufficiently informative. However, dynamical systems evolve over large state spaces, and limited data can often fit multiple distinct equations that explain the observations equally well, leading to identifiability gaps and incorrect recovery of the true dynamics. We introduce LLM-ACES or LLM-guided Active Closed-loop Equation Search, a closed-loop framework that jointly optimizes data acquisition and hypothesis generation under a constrained simulation budget. LLM-ACES leverages LLMs to construct structured, domain-informed hypothesis spaces via a two-stage process: high-level prior induction followed by candidate equation generation within each prior. To resolve ambiguity among competing hypotheses, we introduce an active data selection strategy that identifies regions of maximal predictive divergence among candidate equations and queries the system to obtain informative trajectories. This induces a feedback loop in which hypotheses guide data acquisition and newly acquired data refine the hypothesis space. Experiments demonstrate that LLM-ACES achieves more accurate equation recovery than prior state-of-the-art methods. Our ablations and analyses highlight the importance of coupling hypothesis construction with feedback-driven data acquisition for reliable discovery of dynamical systems.

The rapid proliferation of Large Language Models (LLMs) has created a diverse ecosystem and motivated model routing as a way to navigate differences in architectures, capabilities, latency, and cost. Yet current routing methods still face bottlenecks in generalization, scalability, and interpretability. To solve these problems, we argue that model routing can be formulated as a recommendation problem. This formulation links routing bottlenecks to problems long studied in recommendation systems (RecSys), including cold start, large-scale recommendation, dynamic adaptation, and explainable decision-making. Building on this RecSys perspective, we organize a roadmap that maps major routing bottlenecks to established RecSys paradigms, providing a practical foundation for adapting mature recommendation methodologies to multi-LLM orchestration. We further present preliminary empirical case studies showing that recommendation-inspired routers can achieve strong accuracy-cost trade-offs while supporting model cold-start and interpretable routing behavior.

Scaling improves language-model capability, but it does not necessarily strengthen internal safety mechanisms. We introduce **LLM Rheology**, a representation-level framework for auditing how aligned language models respond to adversarial perturbation inside activation space. Given a learned refusal direction, we define **manifold sensitivity / compliance** as the Fisher--Rao-normalized distributional response induced by controlled activation perturbation. This quantity measures how strongly refusal behavior remains coupled to adversarial task execution in representation space. Across six open model families and 22 checkpoints, including Qwen, DeepSeek-Distill, Mistral, Llama-3, Gemma, and Yi, we observe a recurring geometric scaling pattern. Small aligned models often exhibit elevated refusal response, intermediate-scale models frequently enter weakened-response regimes (*compliance valleys*), and larger checkpoints trend toward near-baseline response consistent with increasing task--refusal decoupling. Cosine measurements on continuous Qwen and DeepSeek scaling axes support this interpretation, showing monotonic decay between refusal and task-generation directions with scale. We further provide causal evidence through inference-time activation intervention on Qwen-72B. Injecting a learned refusal vector at a critical semantic layer restores refusal behavior on the evaluated jailbreak subset while largely preserving benign reasoning performance. Matched-norm placebo vectors fail to reproduce the effect, supporting the directional specificity of the intervention. Together, these results suggest that behavioral refusal can remain surface-level even when internal refusal geometry becomes weakly coupled to adversarial task execution. LLM Rheology provides a complementary representation-level perspective for auditing refusal safety beyond behavioral evaluation.

Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this overlap sparsity is the first-order determinant of wrong deployment decisions: at 5\% pairwise overlap, wrong-decision rates reach 25\% and the probability of selecting the wrong best judge among ten candidates is 65\%. The two actionable levers are overlap quantity and allocation. For quantity, we derive a minimum-overlap formula showing $\rho \geq 0.25$ suffices for non-borderline judges while borderline cases remain fundamentally hard. For allocation, a zero-cost stratified scheme halves false-rejection rates relative to random sampling when strata are informative. We validate on 10 LLM judges across four evaluation matrices spanning visual assessment, causal reasoning, and summarization.

Sign Language Video Generation (SLVG) aims to generate realistic and motion-accurate sign language videos from spoken text. Most existing studies heavily rely on intermediate representations (\eg poses or 3D meshes), and adopt a two-stage generation paradigm, where the text is first converted into poses or other visual modalities, which are then used as conditions to synthesize sign language video frames via diffusion models (\eg pose-to-image models). However, the end-to-end SLVG task remains largely unexplored. In this paper, we demonstrate that end-to-end SLVG is feasible without relying on intermediate representations(\eg poses), and we argue that a key challenge lies in how to generate effective and temporally consistent conditions. With well-designed condition modules, it becomes feasible to build an end-to-end SLVG model without relying on any intermediate modalities. To this end, we propose LLMCond, a first end-to-end text-to-video SLVG framework that requires no auxiliary visual cues during either training or inference. LLMCond consists of four key components: (1) a video VQVAE that compresses sign language videos into a sequence of discrete latent tokens; (2) \textbf{an LLM-based conditioner} that generates temporally and semantically aligned conditions corresponding to the sign sequences; (3) \textbf{a Gaussian Condition Refiner} designed to enforce temporal smoothness across conditions, enabling the generation of coherent and natural sign language motions; and (4) a discrete diffusion model that synthesizes motion-accurate sign language videos conditioned on the refined condition sequences. Extensive experiments on public SL datasets demonstrate that LLMCond achieves highly competitive performance, producing temporally coherent and accurate sign language motions without relying on auxiliary visual modalities such as pose, depth, or optical flow.

Recent work has demonstrated surprisingly good performance of pre-trained LLMs on regression tasks (for example, time-series prediction), with the ability to incorporate expert prior knowledge and the information contained in textual metadata. However we observe major error cascades even in short sequences $\lesssim 100$ points; these models are also computationally intensive and difficult to parallelise. Marginal LLM predictions do not suffer this issue and are trivially parallelised, but can predict over-broad densities. To address this, we propose combining these densities with a lightweight (diffusion-based) neural process. We show that this combination leads to better-calibrated predictions overall, outputs locally consistent trajectories, and leads to text-conditioned function space selection in the meta-learner. As part of this work we propose a gradient-free (and non-Monte Carlo) method for sampling from a product-of-experts of a score model and an `expert' (here the LLM predictive densities). We believe this general method is of independent interest as it is applicable whenever an expert can be convolved with a Gaussian in closed form.

Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood. Prior work shows that aligned models can fail under jailbreak prompts, alternative encodings, and cross-lingual transfer, yet these failures are usually studied as attacks rather than controlled probes of alignment generalization. Moreover, existing evidence is largely grounded in natural language variation already represented during pretraining, leaving unresolved whether alignment generalizes with semantic content or remains tied to superficial surface patterns. In this paper, we study this question using synthetic semantic-preserving transformations that are rule-based and invertible, preserving task-relevant meaning while shifting inputs beyond standard linguistic variation. Across four open-weight and four commercial models, under both fine-tuning and in-context learning, we use these transformations as a probe of alignment generalization and identify an empirical pattern we term **Alignment--utility asymmetry**: once models can operate effectively on transformed inputs, task utility is often substantially retained while alignment failure increases more sharply. For example, adapted GPT-4.1 mini shows only limited utility degradation under transformation while its harmful rate rises from $13.3\%$ to $74.3\%$; Gemini 3 Flash similarly retains near-original utility while its harmful rate increases from $2.3\%$ to $43.0\%$. Taken together, these results suggest that semantic-preserving distribution shifts can expose a recurring gap in how utility and alignment generalize in current LLMs.

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We propose When2Tool, a benchmark of 18 environments (15 single-hop, 3 multi-hop) spanning three categories of tool necessity — computational scale, knowledge boundaries, and execution reliability — each with controlled difficulty levels that create a clear decision boundary between tool-necessary and tool-unnecessary tasks. We evaluate two families of training-free baselines: Prompt-only (varying the prompt to discourage unnecessary calls) and Reason-then-Act (requiring the model to reason about tool necessity before acting). Both provide limited control: Prompt-only suppresses necessary calls alongside unnecessary ones, and Reason-then-Act still incurs a disproportionate accuracy cost on hard tasks. To understand why these baselines fail, we probe the models' hidden states and find that tool necessity is linearly decodable from the pre-generation representation with AUROC 0.89–0.96 across six models, substantially exceeding the model's own verbalized reasoning. This reveals that models already know when tools are needed, but fail to act on this knowledge during generation. Building on this finding, we propose Probe&Prefill, which uses a lightweight linear probe to read the hidden-state signal and prefills the model's response with a steering sentence. Across all models tested, Probe&Prefill reduces tool calls by 48% with only 1.7% accuracy loss, while the best baseline at comparable accuracy only reduces 6% of tool calls, or achieves a similar tool call reduction but incurs a 5× higher accuracy loss. On the real-world Search-o1 agentic benchmark, Probe&Prefill reduces API calls by 20–56% without accuracy degradation.

We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash equilibrium (NE) analysis. To avoid the intractability of equilibrium computation in open-ended text spaces, we model each agent’s action as a mixture over human subpopulations. Agents choose actively and strategically which groups to align with, yielding an interpretable and behaviorally substantive policy class. We derive closed-form NE characterizations, adopting standard concave-utility assumptions to enable analytical system-level predictions and give explicit, actionable guidance for shifting alignment targets toward socially desirable outcomes. The method functions as an active alignment layer on top of existing alignment pipelines such as RLHF. In a social-media setting, we show that a population of LLMs, especially reasoning-based models, may exhibit political exclusion—pathologies where some subpopulations are ignored by all LLM agents—which can be avoided by our method, illustrating the promise of applying the method to regulate multi-agent LLM dynamics across domains.

Video generation enables text-to-video synthesis, video editing, and motion-controlled content creation. However, current video generation models suffer from high computational latency, rendering true real-time capabilities infeasible for down stream tasks. We address this limitation by exploiting the temporal redundancy inherent in video latent patches. To this end, we propose the Latent Inter-frame Pruning with Attention Recovery (LIPAR) framework, which detects and skips recomputing duplicated latent patches. Additionally, we introduce a novel Attention Recovery mechanism that approximates the attention values of pruned tokens, thereby removing visual artifacts arising from naively applying the pruning method. Empirically, our method increases generation throughput by $1.45\times$, on average achieving 12.2 FPS on an NVIDIA A6000 compared to the baseline 8.4 FPS. The proposed method does not compromise generation quality and can be seamlessly integrated with Diffusion Transformer without additional training. Our approach effectively bridges the gap between traditional compression algorithms and modern generative pipelines.

Scaling large recommendation systems requires advancing three major frontiers: processing longer user histories, expanding candidate sets, and increasing model capacity. While promising, transformers' computational cost scales quadratically with the user sequence length and linearly with the number of candidates. This trade-off makes it prohibitively expensive to expand candidate sets or increase sequence length at inference, despite the significant performance improvements. We introduce **LIME**, a novel architecture that resolves this trade-off. Through two key innovations, LIME fundamentally reduces computational complexity. First, low-rank ``link embeddings" enable pre-computation of attention weights by decoupling user and candidate interactions, making the inference cost nearly independent of candidate set size. Second, a linear attention mechanism, **LIME-XOR**, reduces the complexity with respect to user sequence length from quadratic ($O(N^2)$) to linear ($O(N)$). Experiments on public and industrial datasets show LIME achieves near-parity with state-of-the-art transformers but with a 10$\times$ inference speedup on large candidate sets or long sequence lengths. When tested on a major recommendation platform, LIME improved user engagement while maintaining minimal inference costs with respect to candidate set size and user history length, establishing a new paradigm for efficient and expressive recommendation systems.

Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensively studied, personalized robotic manipulation (PeRM) lacks a unified formulation and remains significantly underexplored. In this paper, we identify user preference as the cornerstone of PeRM and introduce LIBERO-PeRM, a novel benchmark designed for personalized preference learning in embodied agents. Specifically, LIBERO-PeRM highlights five key research topics in personalization: 1) how policies follow preferences in zero-shot settings; 2) how to learn single preferences from demonstrations; 3) how efficiently policies acquire preferences as demonstrations increase; 4) how learned preferences generalize across layouts and preference settings; and 5) how policies compose multiple preferences and resolve conflicts. To this end, we propose a unified formulation of personalized manipulation with three preference levels that jointly cover common daily personalization scenarios. Building on this formulation and the LIBERO framework, we develop an extensible procedural generation pipeline that generates paired demonstrations with and without preferences. For benchmarking purposes, we create five task suites (312 tasks in total) with corresponding high-quality demonstrations, rich metadata, and preference satisfaction metrics to probe the aforementioned research topics. Experimental results show that current VLA policies struggle with zero-shot personalization, while SFT makes preferences learnable; preference learning benefits from mixed training, broader layout diversity, and same-layout no-preference data, but generalization, decomposition, and conflict resolution remain difficult.

Long-range geophysical forecasts are fundamentally limited by chaotic dynamics and numerical errors. While data assimilation can mitigate these issues, classical variational smoothers require computationally expensive tangent-linear and adjoint models. Conversely, recent efficient latent filtering methods often enforce weak trajectory-level constraints and assume fixed observation grids. To bridge this gap, we propose Latent Ensemble Variational Data Assimilation (LEVDA), an ensemble-space variational smoother that operates in the low-dimensional latent space of a pretrained differentiable neural dynamics surrogate. By performing four-dimensional ensemble-variational (4DEnVar) optimization within an ensemble subspace, LEVDA jointly assimilates states and unknown parameters without the need for adjoint code or auxiliary observation-to-latent encoders. Leveraging the fully differentiable, continuous-in-time-and-space nature of the surrogate, LEVDA naturally accommodates highly irregular sampling at arbitrary spatiotemporal locations. Across three challenging geophysical benchmarks, LEVDA matches or outperforms state-of-the-art latent filtering baselines under severe observational sparsity while providing more reliable uncertainty quantification. Simultaneously, it achieves substantially improved assimilation accuracy and computational efficiency compared to full-state 4DEnVar.

Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling, and channel dimensionality. As a result, models trained under a fixed spectral configuration often fail to generalize to other sensors. Existing Vision Transformer (ViT) approaches either rely on implicit spectral modeling with fixed channel assumptions or adopt explicit spatial–spectral attention with prohibitive computational cost, leading to a fundamental trade-off between efficiency and expressiveness. In this work, we introduce Low-rank Efficient Spatial–Spectral ViT (LESSViT), a sensor-flexible architecture for cross-spectral generalization. LESSViT is built on LESS Attention, a structured low-rank factorization that models joint spatial–spectral interactions through separable spatial and spectral components, reducing the complexity of full spatial–spectral attention from $\mathcal{O}(N^2 C^2)$ to $\mathcal{O}(rNC)$, where $N$ is the number of spatial tokens, $C$ is the number of spectral channels, and $r$ is the rank of the low-rank approximation. We further incorporate channel-agnostic patch embedding and wavelength-aware positional encoding to support flexible spectral inputs. To enable efficient and robust pretraining, we introduce a hyperspectral masked autoencoder (HyperMAE) with decoupled spatial–spectral masking and hierarchical channel sampling. We evaluate LESSViT under a cross-spectral generalization setting that simulates cross-sensor variability. Experiments on the SpectralEarth benchmark demonstrate that LESSViT improves robustness under spectral shifts while remaining competitive in-distribution, and explicit and efficient spatial–spectral modeling is essential for scalable and generalizable hyperspectral representation learning.