NeurIPS 2026 论文列表

Rip currents are a serious and often under-addressed threat to beach safety, and the leading cause of coastal drownings worldwide. They are difficult to detect due to their amorphous structure, similarity to the background, and large variability in viewpoints and environments. Despite their dangers and growing interest in automated detection, existing research remains fragmented across datasets, metrics, models and approaches, leading to an incomplete understanding of model performance. We introduce RipBench, a unified benchmark that enables controlled evaluation of rip current detection spanning multiple tasks, including classification, axis-aligned and oriented object detection, and instance, semantic, and panoptic segmentation, on the same data with standardized splits. This allows direct comparison of model performance on all levels of visual abstraction. Across $304$ videos ($303{,}491$ frames) collected from diverse coastlines, our results expose a clear performance gap between coarse recognition and precise spatial understanding. While models achieve near-saturated classification performance, accurate localization proves to be a substantially more challenging task, with performance varying across tasks. All tasks are supported with carefully curated annotations and evaluated using both standard and safety-critical metrics, with a focus on the $F_2$ score to emphasize recall in this safety-critical setting. RipBench, along with multiple baseline models per task, is publicly available at \url{https://RipBench.ai} to support progress in real-world, multi-task vision for beach safety.

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose **Orch**estration **R**eward **M**odeling (**Orch-RM**), a self-supervised framework for evaluating orchestration quality without human annotations. Orch-RM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, Orch-RM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. As shown in Figure 1, Orch-RM improves training efficiency by up to 10$\times$ in token usage while improving MAS test-time scaling performance by up to 8\% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Data, code, and trained models will be released upon publication.

Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, allowing agents to learn from joint information while acting from local observations. Ratio-based trust-region methods such as Multi-Agent Proximal Policy Optimization (MAPPO) and Multi-Agent Simple Policy Optimization (MASPO) update decentralized actors using per-agent probability ratios weighted by joint advantage estimates. Teammate non-stationarity increases the variance of these advantages, which in turn increases the variance in the local ratio updates. This exposes two method-specific failure modes: MAPPO's additive clipping removes gradients for outlier samples and weakens recovery from policy drift, while MASPO's soft quadratic penalty can allow probability collapse. We introduce Multi-Agent Ratio Symmetry (MARS), a novel policy optimization objective that replaces these additive ratio-based trust-region mechanisms with a multiplicatively symmetric geometric barrier. MARS preserves corrective gradients while assigning unbounded cost as probability ratios approach zero. Across 47 tasks spanning eight multi-agent environments, including novel JAX benchmarks PaxMen and AeroJAX, MARS matches or exceeds MAPPO and MASPO in aggregate environment-level performance. Ablations show that these gains arise from the geometry of the symmetric barrier rather than from flexible trust-region boundaries alone.

To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. Most existing methods adopt an extracted fact based paradigm: handcrafted static prompts compress raw dialogues into atomic facts, which are then stored, matched, and injected into downstream reasoning. Nevertheless, such fact-centric designs inevitably discard fine-grained details in original dialogues and fail to support deep reasoning over scattered isolated facts. Moreover, static prompts cannot maintain consistent extraction granularity across diverse dialogue styles. To address these limitations, we propose TriMem, which maintains three coexisting representation granularities, including raw dialogue segments anchored by source identifiers for storage fidelity, extracted atomic facts for efficient memory retrieval, synthesized profiles that aggregate dispersed facts into holistic semantic understanding for deep reasoning. We further adopt TextGrad-based prompt optimization, which iteratively refines extraction and profiling prompts via response quality feedback, achieving lifelong evolution without any parameter updating. Extensive experiments on LoCoMo and PerLTQA across multiple LLM backbones demonstrate that TriMem consistently outperforms strong memory baselines.

Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria—relevance, salience, or summary quality. For an agent, however, memory is valuable not because it faithfully describes the past, but because it preserves the distinctions between histories that must remain separated under a fixed budget to support good decisions. We cast this as a decision-centric rate-distortion problem, measuring memory quality by the loss in achievable decision quality induced by compression. This yields an exact forgetting boundary for what can be safely forgotten, and a memory-distortion frontier characterizing the optimal tradeoff between memory budget and decision quality. Motivated by this decision-centric view of memory, we propose **DeMem**, an online memory learner that refines its partition only when data certify that a shared state would induce decision conflict, and prove near-minimax regret guarantees. On both controlled synthetic diagnostics and long-horizon conversational benchmarks, DeMem yields consistent gains under the same runtime budget, supporting the principle that memory should preserve the distinctions that matter for decisions, not descriptions.

Federated Multi-View Learning (FedMVL) enables multiple clients with heterogeneous data views to collaboratively train global models without sharing private data. Existing FedMVL algorithms often overlook the reliability of local predictions, as both uncertainty quantification and calibration remain challenging in privacy-preserving federated settings. Heterogeneous sensing devices yield varying view qualities, but view-isolated training further exacerbates inherent bias of local model, inducing unreliable outputs. Without proper calibration, these artifacts cause spurious cross-view conflicts, ultimately undermining the accuracy and reliability of the aggregated global model. To address these issues, we propose a Reliable Federated Multi-View Learning with evidence calibration (FedRMVL-CAL), a FedMVL framework with adaptive evidence fusion. The local calibration scheme harmonizes uncertainty across views, while the fusion mechanism adaptively reconciles conflicting opinions, enhancing robustness in global inference. Theoretical analysis and extensive experiments demonstrate that FedRMVL-CAL achieves superior accuracy and reliability compared to existing approaches, ensuring trustworthy global predictions across heterogeneous views.

Anchor graphs are a standard route to scalable multi-view clustering, but most existing pipelines still depend on either a shared anchor set sampled from concatenated features or a separate anchor-alignment stage before fusion. Both choices are restrictive: the former hard-codes equal anchor budgets and importance at anchor-construction time, while the latter introduces a cumbersome correspondence problem and still struggles with unequal anchor numbers. We develop an alignment-free probabilistic formulation in which view-specific anchor graphs are noisy manifestations of a shared latent cluster identity rather than objects that require cross-view correspondence. Each view has its own anchor space, number of anchors and cluster prototypes; the only shared latent variable is the sample label. We instantiate this idea with a Gaussian latent-label model and a deterministic prototype M-step. The resulting variational EM algorithm admits closed-form updates with convergence guarantees, while experiments demonstrate competitive clustering performance and practical runtime on most datasets.

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent would reach and the rewards it would collect under any possible course of action. While it has been shown that such information can drastically boost the value, finding the optimal policy is NP-hard, and it is common to apply one of two tractable heuristics: processing the lookahead in chunks of predefined sizes ('fixed batching policies'), and model predictive control. We first illustrate the problems with these two approaches and propose utilizing the lookahead in adaptive (state-dependent) batches; we refer to such policies as adaptive batching policies (ABPs). We derive the optimal Bellman equations for these strategies and design an optimistic regret-minimizing algorithm that enables learning the optimal ABP when interacting with unknown environments. Our regret bounds are order-optimal up to a potential factor of the lookahead horizon $\ell$, which can usually be considered a small constant.

Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principles from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and learning dynamics establish that RecursiveMAS is more efficient than standard text-based MAS and maintains stable gradients during recursive training. Empirically, we instantiate RecursiveMAS under 4 representative agent collaboration patterns and evaluate across 9 benchmarks spanning mathematics, science, medicine, search, and code generation. In comparison with advanced single/multi agents and recursive computation baselines, RecursiveMAS consistently delivers an average accuracy improvement of 8.3\%, 1.2$\times$-2.4$\times$ end-to-end inference speedup, and 34.6\%-75.6\% token usage reduction.

Rare disease diagnosis is a fundamental challenge due to heterogeneous and overlapping clinical phenotypes. While recent LLM-based agentic systems have demonstrated promise by integrating external medical tools and knowledge, they typically rely on large-scale or commercial LLMs, limiting their practical deployment in resource-constrained settings. In this work, we observe that their performance significantly degrades when using small-scale LLMs, due to entangled workflows and unreliable multi-evidence aggregation. To address this issue, we propose RADAR, a rare disease diagnostic framework designed for small-scale LLMs. RADAR adopts a divide-and-conquer paradigm that decouples heterogeneous diagnostic evidence into specialized workflows, reducing reasoning complexity and improving robustness. It further introduces a knowledge-driven self-evaluation mechanism that performs evidence-aware reasoning over structured disease knowledge to produce interpretable reliability scores by identifying key supporting phenotypes and conflicting evidence. Finally, a multi-evidence fusion strategy integrates outputs from multiple sources based on reliability and clinical agreement, resolving conflicts and producing stable diagnostic rankings. Experiments on three benchmarks show that RADAR consistently outperforms various state-of-the-art baselines, including general and medical LLMs and agentic systems. Code will be released.

Learning to collaborate with previously unseen partners is a fundamental generalization challenge, known as Ad Hoc Teamwork (AHT). Existing methods often adopt a two-stage pipeline: first, a fixed population of teammates is generated, and second, an AHT agent is trained to collaborate with them. This separation limits coverage of behaviors and ignores whether the generated teammates are informative for the AHT agent to learn from. On the other hand, AHT agents are typically trained under the assumption that the training teammate set is uncontrollable, despite the fact that its composition strongly influences generalization. This paper presents a unified framework for AHT by reformulating the problem as an open-ended learning process between an AHT agent and an adversarial teammate generator. We introduce ROTATE, a regret-driven, open-ended training algorithm that alternates between improving the AHT agent and generating teammates that probe its collaboration deficiencies. Experiments across Overcooked and Level-Based Foraging tasks demonstrate that ROTATE significantly outperforms baselines on an unseen set of teammates, establishing a new standard for robust, generalizable teamwork.

LLM-based multi-agent systems (MAS) improve complex reasoning through collaborative decomposition, verification, and synthesis, but their performance can degrade sharply when compromised agents inject misleading intermediate messages. Existing topology methods rely on fixed communication patterns or query-adaptive graphs, but rarely infer or intervene runtime reliability risk, leaving them fragile when compromised agents vary across queries. We study stochastic adversarial topology adaptation, where compromised agents shift across graph positions and rare cascades dominate the high-loss tail. To address this setting, we propose RIGOR, a topology-adaptation framework that couples runtime risk inference with tail-aware training. RIGOR combines Risk-Gated Topology Construction (R-GTC), which probes agent behavior, estimates per-agent risk, and edits the graph through soft quarantine and edge masking, with CVaR-Guided Robust Optimization (C-GRO), which trains the editor on high-loss episodes rather than average gain alone. Across six benchmarks and two backbones, RIGOR consistently outperforms existing MAS baselines under query-varying misleading-message attacks, achieving an average 21.09\% accuracy improvement over the strongest baseline on Qwen3.5-35B-A3B. Tail-subset and position-wise analyses further show that these gains stem from improved robustness against worst-case cascades and dynamically changing compromised-agent positions. The code is available for anonymous access at https://anonymous.4open.science/r/RIGOR-0D7D.

Multi-agent systems (MAS) have emerged as a dominant paradigm where agent routing is a bottleneck for balancing performance and cost. However, existing agent routing methods suffer from the prohibitive cost of exhaustive benchmark construction and the neglect of query complexity essential for mixed tasks. To address this issue, we propose the RADAR (Routing Agents via Difficulty-Aware Recovery) framework. RADAR enables accurate decision-making under limited evaluation cost through two complementary modules. MatrixComp module employs structure-aware matrix completion to recover global performance profiles from sparse observations. Furthermore, DiffMatch module extracts reasoning meta-features for fine-grained alignment via a difficulty-calibrated retrieval mechanism. Extensive experiments demonstrate that RADAR maintains performance equal with state-of-the-art baselines while reducing the cost of benchmark construction by at least 33%.

Recent advances in online learning have achieved an $O(n/\Delta_{[2]})$ query complexity in quantum $n$-arm multi-armed bandits (MABs) for best-arm identification, which represents a quadratic speedup over their classical counterparts. Here and throughout, $\Delta_{[2]}$ is the gap between the mean of the best and second-best arms. However, the implementations of these algorithms remain on a small scale due to various aspects of quantum hardware restrictions. One of the most significant restrictions is \emph{memory decoherence}, in which the qubits quickly lose information after a short period of time. Memory decoherence can occur at \emph{intra-circuit} and \emph{inter-circuit} levels. Intra-circuit decoherence happens often in near-term quantum computers, where the noise becomes overwhelming when the circuit is deep. On the other hand, inter-circuit decoherence captures future quantum machines, where a quantum memory is promising, but objects stored in the memory for too long can still become decoherent. In this paper, we present a comprehensive treatment of both memory decoherence problems. For inter-circuit decoherence, we derive a framework based on streaming bandits, and we obtain an algorithm that finds the best arm with high constant probability using $O(n/\Delta_{[2]})$ queries and an $O(\log{n})$ decoherence window. This is the first quantum algorithm for MABs that achieves an $o(n)$ decoherence window, which represents an exponential improvement. For intra-circuit decoherence, we observe that only $O(1)$-depth circuits can be used to avoid significant decoherence. Therefore, we devise various hardware optimizations and a destructive SWAP test subroutine to speed up the empirical performance. On the IBM Q System One machine with 127 qubits, our implementation scales the quantum MABs to over $1000$ arms, and our algorithms consistently achieve significant efficiency improvements over classical bandit algorithms in both physical experiments and computer simulations.

The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with distinct design principles have been proposed in recent years. Instead of proposing a new QD algorithm, this work introduces a novel reformulation by casting the QD optimization as a multi-objective optimization (MOO) problem with a huge number of optimization objectives. By establishing this connection, we enable the direct adoption of well-established MOO methods, particularly set-based scalarization techniques, to solve QD problems through a collaborative search process. We further provide a theoretical analysis demonstrating that our approach inherits theoretical guarantees from MOO while providing desirable properties for the QD optimization. Experimental studies across several QD applications confirm that our method achieves performance competitive with state-of-the-art QD algorithms.

Quantitative analysis of animal behavior in neuroscience increasingly relies on accurate 3D pose, yet current large-scale mouse datasets are restricted to top-down views and suffer from occlusion and keypoint ambiguity. We introduce QDMouse4M, a six-view dataset of freely moving mice with physically grounded 2D and 3D keypoint annotations obtained from subdermal quantum-dot fluorescence markers. QDMouse4M contains over four million reflectance frames with matched fluorescence frames, 2D and 3D pose trajectories and behavior classifications. We use the dataset to evaluate markerless 2D and 3D pose estimation with SLEAP and Lightning Pose 3D across training-set sizes, backbones, and in-session/out-of-session splits. We further show that the released trajectories support downstream spontaneous-behavior analysis with Keypoint-MoSeq and stride-level gait measurements. QDMouse4M provides a benchmark-scale, physically grounded resource for developing and evaluating pose estimation, behavior understanding, and biomechanics models under realistic dark-environment laboratory conditions.

Multi-agent systems (MASs) are increasingly deployed for complex tasks, yet their security against indirect prompt injection remains poorly understood. As frontier LLMs become more robust to injections with overtly malicious semantics, such as credential exfiltration, unauthorized transactions, or policy bypass, the residual attack surface shifts to task hijacking: an injection that silently redirects an MAS toward an attacker-chosen alternative task plausibly within the agent's domain, such as the wrong patient's record, a competitor's product, or a different CVE. There is no malicious verb to refuse, and existing benchmarks, designed around overtly malicious goals in single-agent settings, do not characterize this surface. We introduce PurpleAudit, an auditing framework that lets a practitioner stress-test their own MAS against task hijacking and derive a tailored system-prompt defense. The framework couples 22 baseline attacks and four prompt/tool-level defense baselines from the literature with a co-evolutionary purple-team procedure, in which red- and blue-team agents evolve stronger attacks and adaptive defenses by reasoning over each other's execution traces. Applied across frontier backends on ten MASs and a real-world MAS with live web access, PurpleAudit surfaces an MAS-specific attack pattern that frames the injection as a prerequisite for completing the user's task, reaching 31.26% ASR on Claude Opus 4.5 under the framework's auditing protocol, where 22 baseline attacks fail entirely. The co-evolved defense suppresses both baseline and evolved attacks at negligible utility cost, transfers across reasoning-capable backends, and operates at the prompt level with low deployment overhead.

Large language models (LLMs) have shown strong performance in single-table reasoning but struggle to generalize to multi-table scenarios due to schema heterogeneity, long input contexts, and the lack of structural awareness. We introduce StrucTab-R1, a schema-centric reasoning framework that decouples relational reasoning from raw data exposure. Our approach encodes relational databases as heterogeneous schema graphs, where tables, columns, and foreign-key constraints form distinct node and edge types, and employs a heterogeneous graph encoder with question-conditioned cross-attention pooling to distill compact, semantically grounded schema tokens. Rather than serializing table rows into the context, the LLM plans over the schema representation and emits a Chain-of-Execution: an executable reasoning trace that first identifies the relevant schema subgraph and then performs a sequence of composable tool-function calls (e.g., filter, join, aggregate). These calls are executed externally, with compact observations returned to support subsequent reasoning steps. This design confines the model's attention to relevant subgraphs, mitigating hallucinations in multi-hop join reasoning. To further improve reliability, we train the model with supervised traces followed by structure-aware reinforcement learning, where the reward jointly optimizes answer correctness, schema-region precision, and execution consistency. Experiments on single-table and multi-table benchmarks show that StrucTab-R1 improves execution accuracy over strong general-purpose and table-specialized LLMs and remains effective on large-schema settings where raw-context baselines fail.

Many recent math- and science-oriented agent systems adopt hierarchical designs with specialized reviewer roles, motivated by the idea that routing critique through a dedicated review stage should help turn wrong candidates into correct ones on hard problems. We study that expectation on 4,181 verifier-grounded Omni-MATH problems, a hard ten-tier benchmark with enough headroom to separate protocols, using matched gpt-oss-120b actors as the primary actor family. On tiers 1-2, multi-agent collaboration adds at most about 2 percentage points over the matched single-agent baseline. From tier 4 onward, the gains open sharply, reaching about 10 to 20 percentage points on tiers 6-9. In that regime, broadcast-style peer discussion attains higher final accuracy than a planner-executor-reviewer pipeline (PER). We use that divergence as a starting observation and ask when reviewer quality translates into effective solver updates. On this benchmark, the PER-broadcast accuracy gap is not accounted for by reviewer precision alone. Here reviewer precision asks how often a reviewer warning truly points to a real error. PER's reviewer has higher precision (0.861 vs. 0.644), yet correct critique is much less likely to change the next candidate the protocol carries forward, and reviewer-guided repair is correspondingly lower. These results show that reviewer detection quality and critique uptake are empirically separable. Within matched PER interventions, forcing explicit acknowledgment lowers final accuracy instead of improving follow-through, while placing reviewer guidance directly in the solver's working context partially improves follow-through without closing the gap. Taken together, these interventions point in the same direction: critique appears more likely to be acted upon when it is presented more directly in the solver's working context, although this evidence is directional rather than causal. Under reviewer-centric evaluation, a system can look strong at spotting errors yet still fail to solve more problems if the protocol does not act on those critiques.