NeurIPS 2026 论文列表

Speculative decoding accelerates Large Language Models via draft-then-verify, where verification can be framed as an Optimal Transport (OT) problem. Existing approaches typically handle multi-draft and multi-step aspects in isolation, applying either flat OT to single-step drafts or per-token rejection sampling to tree-structured candidates. This separation leaves the joint regime (where multi-step dependencies meet multi-draft branching) poorly optimized, as local verification rules fail to exploit the coupling between horizontal and vertical dimensions of candidate trees. In this paper, we propose a unified perspective that casts tree-based verification as a conditional OT problem. Our key insight is that vertical dependencies can be abstracted through prefix acceptance probabilities, which act as dynamic scaling factors to actively guide horizontal draft selection. Based on this principle, we introduce UniVer, a verification algorithm that jointly optimizes across tree levels by composing local optimal transport plans under prefix constraints. We prove that UniVer remains lossless and achieves the optimal acceptance rate under the proposed conditional framework. Extensive experiments across different tasks and models demonstrate that UniVer improves acceptance length by 4.2\% to 8.5\% over standard recursive rejection sampling without replacement, while maintaining exact distributional alignment with the target model.

Multi-view transformers solve 3D vision tasks in a single feed-forward pass, yet their internal mechanisms remain poorly understood. We view their residual layers as progressively updating a latent state, and study how this state evolves during 3D reconstruction. To make the state geometrically interpretable, we train layer-wise probes that decode intermediate tokens into 3D pointmaps, yielding intermediate 3D reconstructions throughout the network. This view recasts feed-forward 3D reconstruction as progressive refinement rather than a single reconstruction step, with most layers improving reconstruction. Convergence speed varies across models and sample difficulty, with slower convergence on difficult samples. We further analyze these updates and find consistent, complementary roles for single-view and cross-view attention. Cross-view attention improves multi-view alignment, while single-view attention refines intra-view geometry and compensates for points visible in only one view. Finally, we identify cross-view attention heads that specialize in correspondence matching. We show that their correspondences are jointly refined with the reconstructed geometry, and that selected heads can be partially replaced by analytical correspondences. Our analysis provides a direct view of the reconstruction process inside multi-view transformers, and suggests a first step toward replacing emergent mechanisms with analytical operations. The code used for the analysis will be made available.

Multi-Agent Systems (MAS) are a promising paradigm for improving the reasoning capabilities of large language models, yet they remain prone to hallucinations and erroneous outputs. Uncertainty Quantification (UQ) is crucial for assessing system reliability, but existing methods are largely designed for single-agent settings; how to exploit MAS structure for UQ while keeping inference cost-neutral remains underexplored. We propose UMAS, a parameter-free, cost-neutral, system-level UQ framework that estimates the credibility of inter-agent influence from each generation’s intrinsic confidence. UMAS uses these credibility signals to modulate how uncertainty is updated at each node, and then aggregates node-level uncertainty into a system-level estimate. Extensive evaluations on Debate and DyLAN across diverse benchmarks show that UMAS consistently outperforms state-of-the-art baselines by an average of 10.49 AUROC points. Beyond uncertainty estimation, UMAS enables hallucination detection and uncertainty-aware answer selection, improving MAS accuracy by up to 12.6 points on specific tasks while enhancing reliability.

Calibrated predictions are useful because their numerical values can be interpreted as probabilities. Calibration errors are therefore widely used to evaluate and compare probabilistic predictors. Recently, Haghtalab et al. [2024] introduced truthfulness as an additional requirement for such measures. A calibration measure is truthful if a predictor minimizes its expected measured error by reporting the true conditional label distribution. Many standard empirical calibration errors are non-truthful: a predictor may appear better calibrated by distorting its probabilities. We study the implications of truthful and non-truthful calibration errors for practice. First, we introduce perfectly truthful calibration errors for full multiclass calibration and classwise calibration, two standard multiclass notions. More generally, our construction applies to any linear property of the label distribution, generalizing the truthful calibration error for binary predictions in Hartline et al. [2025]. We also identify a truthful correction for confidence calibration. Second, we characterize the decision-theoretic implications of these truthful errors. For calibrated predictors, truthful calibration errors preserve the Blackwell dominance: a more informative calibrated predictor receives no larger expected error. Third, we show that this decision-theoretic interpretation explains and mitigates the well-observed ranking robustness problem of binned calibration errors. Empirically, non-truthful confidence-based errors can reverse model rankings when the number of bins changes, while our truthful classwise error gives more stable rankings across binning choices.

Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by combining multiple images. However, existing approaches either mix only pairs of images or rely on fixed small layouts, limiting control over source count, visible area proportions, and induced supervision. We propose TreemapMix, a distribution-controlled multi-image augmentation that samples source weights from a Dirichlet distribution and assigns them to area-proportional regions using a treemap partition. The resulting known region areas support two complementary objectives. TreemapMix with soft cross-entropy (SCE) treats areas as soft class-probability targets, while TreemapMix with a Plackett-Luce (PL) objective converts areas into ordinal supervision. On ImageNet-1K under a matched training protocol, TreemapMix-SCE achieves substantially lower calibration error than evaluated mixed-sample baselines, while TreemapMix-PL achieves the strongest Top-1 accuracy. Transfer experiments on object detection and instance segmentation suggest that TreemapMix-pretrained features remain useful beyond classification. These results show that controlled multi-image composition can expose the same region-area information as either probability-matching or rank-matching supervision.

Recent progress in computer vision has produced a wide range of powerful specialized models for detection, segmentation, counting, and other visual tasks. However, these models are usually optimized for isolated task formulations, making it difficult to directly support general-purpose visual intelligence, especially when a task requires complex language understanding and dense small-object perception. In this paper, we propose VisHarness, a trainable visual agent that decouples high-level perception, reasoning, and decision-making from low-level task execution. Instead of training a model to solve a specific visual task, VisHarness learns to harness a set of carefully designed heterogeneous visual experts. This paradigm preserves the general intelligence of the agent while fully leveraging the precision advantages of specialized visual models in concrete visual tasks. With only lightweight training, VisHarness learns a generalizable visual expert-harnessing policy and can solve common fundamental vision tasks under various complex conditions through multi-turn interactions with visual expert models. To enable efficient on-policy reinforcement learning training in a live environment, we introduce dynamic visual memory archiving, which mitigates the rapidly accumulating visual-token overhead caused by multi-turn interactions with visual expert models. Experiments on four representative benchmarks covering reasoning segmentation, generalized referring segmentation, dense small-object detection, and referring counting demonstrate that VisHarness substantially outperforms existing general-purpose models and achieves competitive or superior performance compared with task-specific models.

While LLMs excel at isolated coding tasks, their ability to perform autonomous, long-horizon machine learning (ML) development remains bottlenecked by poor strategic planning. Because current benchmarks rely on outcome-based metrics, they obscure process-level failures, making it impossible to diagnose where agent strategies diverge from human expertise. To solve this, we introduce TraceML, the first large-scale dataset of paired human and agent trajectories for long-horizon ML tasks. TraceML contains 4{,}672 Kaggle trajectories across 134 MLE-bench competitions, with 430 expert humans paired head-to-head with 207 LLM-agent runs on 7 of those competitions. Using a unified extraction schema to analyze step-by-step behavior, we reveal systematic gaps: agents execute local edits well but exhibit unstructured exploration, poor experiment prioritization, and weak long-term memory attribution compared to experts. Translating these diagnostic insights into action, we design a novel, planning-oriented agent harness based on human priors that significantly improves both process efficiency and final competitive performance.

Large Language Models (LLMs) are increasingly deployed in real-world settings where alignment with diverse human values is essential. However, existing alignment methods are often costly, obscure underlying value heterogeneity, and offer limited interpretability. In this work, we move toward multi-human-value alignment through inference-time intervention by investigating how different values are internally represented within LLMs. We propose a probing-based value localization framework that identifies value-sensitive components, i.e., value heads, which mediate model behavior across multiple moral and normative dimensions such as harmlessness, honesty, and helpfulness. Analyses across multiple LLM families reveal that value heads are universally sparse and exhibit structured interactions, including conflicts among certain values. These components demonstrate clear functional specialization: selectively ablating value heads induces substantial and value-specific behavioral changes. Building on these findings, we introduce an inference-time intervention strategy that enables controllable adaptation of LLMs to single or multiple human value systems, with theoretical support for its effectiveness. Experiments on human-value benchmarks demonstrate that our method improves flexible and faithful value alignment while maintaining overall model performance, highlighting mechanistic interpretability as a foundation for socially aware, pluralistic AI.

Semantic fidelity is essential for multi-agent communication under non-ideal channels, comprising transmission fidelity and conversion fidelity. Yet existing numerical and neural message formats cannot simultaneously achieve both. To address this, we propose a novel message format-\textbf{H}yperdimensional \textbf{S}ymbolic \textbf{M}essages (HSM), and its corresponding communication framework \textbf{Herm}. For transmission fidelity, Herm suppresses semantic entanglement via an entity-attribute-value structured encoding pipeline. For conversion fidelity, Herm first leverages a receiver-centric ego-binding mechanism to align semantics. Then, a similarity-aware dual-branch fusion module is proposed to prevent critical semantic dilution. To realize explicit message-semantic conversion, we devise an iterative decoding scheme via algebraic inverse operation. Experiments exhibit that Herm outperforms baselines across various noisy scenarios while maintaining superior structural readability.

Modern autonomous driving systems widely adopt multi-view Bird’s-Eye-View (BEV) based 3D perception models due to their superior performance. Despite their success, the robustness of these models against adversarial camouflage attacks remains largely unexplored. Existing camouflage attacks primarily target single-view 2D detectors, limiting their effectiveness in multi-view 3D perception settings. To address this gap, we propose BEVCA, a novel adversarial camouflage generation framework tailored for multi-view BEV-based 3D perception. Our framework integrates a BEV-feature-based adversarial loss with a multi-view neural rendering module, enabling effective and transferable camouflage attacks across different models and tasks. Extensive experiments in both digital and physical settings demonstrate that BEVCA outperforms state-of-the-art baselines and exhibits strong robustness under real-world conditions.

Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which discards the parallel structure and incurs redundant prefill computation. In this work, we introduce Parallel-Synthesis, a plug-and-play framework that enables a synthesizer to directly consume the KV caches produced by parallel worker agents. Parallel-Synthesis combines a cache mapper that calibrates independently generated branch caches with a fine-tuned synthesizer adapter that enables generation from this non-sequential cache interface. We train Parallel-Synthesis using data that exposes the synthesizer to parallel cache contexts, teaches aggregation across cached branches, and distills reasoning behavior from standard text-concatenation-based synthesis. Across nine downstream datasets spanning math, science QA, code generation, GAIA, and multi-agent database diagnosis, Parallel-Synthesis matches or outperforms text-based synthesis on seven datasets and remains close on the other two. It also reduces time-to-first-token by 2.5×--11×, suggesting that direct cache-based synthesis is a promising interface for more native and efficient synthesis over parallel agent branches.

Generating codes from UI screenshots has recently benefited from MLLMs, yet existing methods centered on HTML targets and transfer poorly to multi-frameworks such as React, Vue, and Angular. However, unlike HTML, which does not entail compilation issues, generating executable code in multi-framework settings is more challenging due to framework-specific differences in syntax and failure modes, as well as the need to maintain global consistency across files. To address this problem, we study executable multi-framework front-end code generation and propose MESCoder, a tree-structured self-corrective generation framework. Our method first extracts a structural scaffold from the screenshot and then constructs sub-trees and assembly relations step by step, transforming large project generation into a sequence of localized decisions. On top of this scaffold, we introduce a unified Project Agent that continuously revises its own partial project under runtime sandbox feedback and dynamically chooses between local repair and cluster level repair. For training, we adopt a two-stage strategy that first initializes the policy offline to learn basic multi-framework generation and repair priors, and then refines it with online reinforcement learning to optimize long horizon executability and final page quality. The resulting framework models multi-framework executability as a conditioned project state transition process and improves the stability and quality of complex front end generation through self correction. Experiments show that our method improves executability, while narrowing the visual-fidelity gap to HTML-based generation.

Printed circuit boards (PCBs) are the hardware foundation of modern electronic systems. However, automating PCB schematic design remains difficult. A valid schematic must respect real-IC pin-level constraints and cross-component topological relations, neither of which is captured by generic simulation, local rule checks, or direct LLM generation. To address this challenge, we present TopoScope, a training-free LLM agent that uses the schematic graph not only as the final output, but also to guide generation and verification at runtime. TopoScope couples two mechanisms: Topology-Guided Context Scoping, which computes a scoped view for each component-level wiring decision, and Pattern-Based Rule Verification, which expresses datasheet-derived electrical constraints as graph patterns and uses them as in-loop feedback. We also introduce a 20-design benchmark spanning three complexity tiers and six application domains, with functional assertions evaluated on the generated schematic graph and calibrated against expert judgments. Across seven recent LLMs, TopoScope improves functional correctness, reduces invalid graph references, and enables more reliable generation of medium and hard multi-IC schematics compared with knowledge-provided baselines.

Topological clustering, and its main algorithm ToMATo, is a clustering method from Topological Data Analysis (TDA) which has been applied successfully in several applications during the last few years. This is thanks to its high versatility, as clusters are detected from the persistent components in the sublevel sets of any user-defined function (gene expression, pixel values, etc), and efficiency, as topological clustering enjoys robustness guarantees. However, ToMATo is also limited in several ways. First, a graph on the data points needs to be provided as a hyper-parameter of the method (whose fine-tuning is left to the user). Second, ToMATo is known to be very sensitive to outlier values in the function range. Finally, and most importantly, ToMATo can only handle one function at a time, whereas it is critical to use several functions in various applications. In this article, we introduce ToMAToMP: the first topological clustering method able to handle several functions at the same time with theoretical guarantees. More specifically, we leverage a recent tool from multi-parameter persistent homology, called MMA decomposition, to design our clustering algorithm, and prove that it enjoys robustness properties. As corollaries, we show that it can be used to make ToMATo independent of graph tuning, and robust to outliers. Finally, we provide a set of numerical experiments showcasing the efficiency and quality of the clusterings produced by ToMAToMP, by showing strong improvement over non-topological and topological baselines for various datasets.

Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness perspectives. We address this gap by proposing a comprehensive definition of trustworthiness inspired by human communication theory \citep{grice1975logic}. Our definition identifies six orthogonal trust dimensions that provide interpretable measures of trustworthiness. Building on this definition, we introduce the Attention Trust Score (A‑Trust), a lightweight, attention‑based method for evaluating the trustworthiness of messages. We then develop a principled trust management system (TMS) for LLM‑MAS that supports both message‑level and agent‑level trust assessments. Experiments across diverse multi‑agent settings and tasks demonstrate that our TMS significantly improves robustness against malicious inputs.

Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather, where solving a task often requires both numerical accuracy and contextual reasoning. Recent progress has moved from specialized neural predictors to approaches built on LLMs and foundation models that can reason over time series inputs and use external tools. However, most such systems remain execution-centric: they focus on solving the current instance but learn little from exploratory execution. This is especially limiting in verifiable numeric settings, where multiple candidate executions and tool-use procedures may all be task-valid yet differ sharply in quantitative quality, and where early success can trigger tool-prior collapse that suppresses further exploration. To address this limitation, we present TimeClaw, an exploratory execution learning framework that turns exploratory execution into reusable hierarchical distilled experience through a four-stage loop: Explore, Compare, Distill, and Reinject. TimeClaw combines metric-supervised exploratory execution learning, task-aware tool dropout, and hierarchical distilled experience for inference-time reinjection, while keeping the base model frozen and avoiding online test-time adaptation. In an MTBench-aligned evaluation with 17 tasks that span finance and weather prediction and reasoning tasks, TimeClaw delivers consistent gains over the baselines. These results suggest that, for scientific systems, the bottleneck is not only execution-time capability, but how exploratory experience is compared, distilled, and reused.

Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-\beta})$ where the regime exponent $\beta$ classifies any configuration into one of three asymptotic regimes --- hard-ceiling at $1/c$ ($\beta = 0$), sublinear at $N^\beta/c$ ($0 < \beta < 1$), or linear ($\beta \ge 1$), and a mean-field theorem predicts that peer count $k$ and rounds$\tau$ during agent debate enter the dynamics only through their product $k\tau$. The law applies at two levels: answer diversity and correctness redundancy. Across 44 (model $\times$ task $\times$ condition) cells spanning peer debate, self-correction, random-noise placebo, self-consistency, three open-weight families (Qwen, Llama, Ministral) at scales from 7B to 32B with a frontier API check (Gemini), thinking models, heterogeneous teams, and sparse communication, the functional form fits every condition at $R^2 > 0.99$; only $(c, \beta)$ shifts. On free-form math, dense peer influence collapses the answer-level regime from sublinear into hard-ceiling; correctness-level fits remain hard-ceiling throughout. Three findings have practical implications. \emph{(i)}~Thirty dense debating agents produce no more answer diversity than one on MMLU-Hard. \emph{(ii)}~A noise placebo tracks self-correction on free-form math and at $4\times$ scale, so within homogeneous teams the gain commonly attributed to ``debate'' comes from re-evaluation, not peer content. \emph{(iii)}~A single $N \le 5$ pilot predicts the $N=30$ structural ceiling, and within the configurations tested only architectural diversity (heterogeneous teams) lowers $c$ and escapes the hard-ceiling regime, communication-mode interventions do not.

Many learning systems are performative: once deployed, their predictions change the data distribution on which future models are trained. In multi-agent settings, this feedback is routed through a network of interacting learners, so stability depends not only on the strength of performativity but also on who affects whom. We study repeated retraining in multi-agent performative prediction and identify a spectral threshold, derived from primitive sensitivity and curvature parameters, that separates stable learning guarantees from worst-case learning obstruction. Prior work often collapses cross-agent feedback into a scalar contraction constant, missing this network structure. We instead introduce the reflexivity matrix $\Gamma$, which records how strongly one agent's deployment can move another agent's best response, defined from per-agent gradient sensitivities and curvature parameters. The threshold occurs when the spectral radius of this matrix crosses one. Below the threshold, repeated retraining converges geometrically to a unique performatively stable equilibrium, with cumulative excess loss bounded uniformly in the time horizon. Above the threshold, we construct supercritical instances in which decentralized learning provably fails: every local-information learner incurs cumulative excess loss that grows linearly in the horizon. Together, these results characterize this threshold behavior through upper and lower bounds and recover the single-agent scalar threshold from prior work as a special case.

Communication is fundamental to sustaining reciprocity and cooperation in strategic interactions. We identify and formulate the _influence attribution problem_ as the central optimization difficulty inherent in such dynamics for a learning agent: any action or signal the agent emits reshapes the reputations of many third parties along combinatorially branching paths before feeding back into its own future rewards, forcing the agent to account for all of these indirect channels at once when choosing every action. To address this, we introduce the _reciprocity gradient_, which explicitly backpropagates reward gradients through private estimators of opponents' policies trained from public observations. The gradient flows through the reputation chain itself analytically, rather than being estimated from sampled returns. It jointly optimizes actions and evaluative signals without intrinsic rewards or reward shaping. Empirically, the method recovers near-optimal context-sensitive policies, while sample-based baselines collapse into constant-output policies.