AAAI 2026 论文列表

Proactive intention decoding remains a critical yet underexplored challenge in brain–machine interfaces (BMIs), especially under naturalistic, self-initiated behavior. Existing systems rely on reactive decoding of motor cortex signals, resulting in substantial latency. To address this, we leverage the common marmoset’s spontaneous vocalizations and develop a high-resolution, dual-region ECoG recording paradigm targeting the prefrontal and auditory cortices and a neural decoding framework that integrates shapelet-based temporal encoding, position-aware attention, frequency-aware channel masking, contrastive clustering and a minimum error entropy-based robust loss. Our approach achieves 91.9% accuracy up to 200 ms before vocal onset—substantially outperforming 13 competitive baselines. Our model also uncovers a functional decoupling between auditory and prefrontal regions. Furthermore, joint modeling in time and frequency domains reveals novel preparatory neural signatures preceding volitional vocal output. Together, our findings bridge the gap between foundational neuroscience and applied BMI engineering, and establish a generalizable framework for intention decoding from ecologically valid, asynchronous behaviors.

Extracellular recordings are transient voltage fluctuations in the vicinity of neurons, serving as a fundamental modality in neuroscience for decoding brain activity at single-neuron resolution. Spike sorting, the process of attributing each detected spike to its corresponding neuron, is a pivotal step in brain sensing pipelines. However, it remains challenging under low signal-to-noise ratio (SNR), electrode drift, and cross-session variability. In this paper, we propose HuiduRep, a robust self-supervised representation learning framework that extracts discriminative and generalizable features from extracellular recordings. By integrating contrastive learning with a denoising autoencoder, HuiduRep learns latent representations robust to noise and drift. With HuiduRep, we develop a spike sorting pipeline that clusters spike representations without ground truth labels. Experiments on hybrid and real-world datasets demonstrate that HuiduRep achieves strong robustness. Furthermore, the pipeline significantly outperforms state-of-the-art tools such as KiloSort4 and MountainSort5 on accuracy and precision on diverse datasets. These findings demonstrate the potential of self-supervised spike representation learning as a foundational tool for robust and generalizable processing of extracellular recordings.

Explainable AI (XAI) methods generally fall into two categories. Post-hoc approaches generate explanations for pre-trained models and are compatible with various neural network architectures. These methods often use feature importance visualizations, such as saliency maps, to indicate which input regions influenced the model’s prediction. Unfortunately, they typically offer a coarse understanding of the model’s decision-making process. In contrast, ante-hoc (inherently explainable) methods rely on specially designed model architectures trained from scratch. A notable subclass of these methods provides explanations through prototypes, representative patches extracted from the training data. However, prototype-based approaches require dedicated architectures, involve specialized training procedures, and perform well only on specific datasets. In this work, we propose EPIC (Explanation of Pretrained Image Classification), a novel approach that bridges the gap between these two paradigms. Like post-hoc methods, EPIC operates on pre-trained models without architectural modifications. Simultaneously, it delivers intuitive, prototype-based explanations inspired by ante-hoc techniques. To the best of our knowledge, EPIC is the first post-hoc method capable of fully replicating the core explanatory power of inherently interpretable models. We evaluate EPIC on benchmark datasets commonly used in prototype-based explanations, such as CUB-200-2011 and Stanford Cars, alongside large-scale datasets like ImageNet, typically employed by post-hoc methods. EPIC uses prototypes to explain model decisions, providing a flexible and easy-to-understand tool for creating clear, high-quality explanations.

Multi-Agent Reinforcement Learning (MARL) has gained significant interest in recent years, enabling sequential decision-making across multiple agents in various domains. However, most existing explanation methods focus on centralized MARL, failing to address the uncertainty and nondeterminism inherent in decentralized settings. We propose methods to generate policy summarizations that capture task ordering and agent cooperation in decentralized MARL policies, along with query-based explanations for “When,” “Why Not,” and “What” types of user queries about specific agent behaviors. We evaluate our approach across four MARL domains and two decentralized MARL algorithms, demonstrating its generalizability and computational efficiency. User studies show that our summarizations and explanations significantly improve user question-answering performance and enhance subjective ratings on metrics such as understanding and satisfaction.

State-of-the-art methods for Human-AI Teaming and Zero-shot Cooperation focus on task completion i.e. task rewards, as the sole evaluation metric while being agnostic to `how' the two agents work with each other. Furthermore, subjective user studies only offer limited insight into the quality of cooperation existing within the team. Specifically, we are interested in understanding the cooperative behaviors arising within the team when trained agents are paired with humans - a problem that has been overlooked by the existing literature. To formally address this problem, we propose the concept of constructive interdependence - measuring how much agents rely on each other’s actions to achieve the shared goal - as a key metric for evaluating cooperation in human-agent teams. We measure interdependence in terms of action interactions in a STRIPS formalism, and define metrics that allow us to assess the degree of reliance between the agents' actions. We pair state-of-the-art agents with learned human models as well as human participants in a user study for the popular Overcooked domain, and evaluate the task reward and teaming performance for these human-agent teams. While prior work has claimed that state-of-the-art agents exhibit cooperative behavior based on their high task rewards, our results reveal that these agents often fail to induce cooperation, as evidenced by consistently low interdependence across teams. Furthermore, our analysis reveals that teaming performance is not necessarily correlated with task reward, highlighting that task reward alone cannot reliably measure cooperation arising in a human-agent team.

In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can inadvertently erode human trust and cause them to ignore AI advice precisely when it is most needed. Conversely, an aligned AI fosters trust yet risks reinforcing suboptimal human behavior and lowering human-AI team performance. In this paper, we start by identifying this fundamental tension between performance-boosting (i.e., complementarity) and trust-building (i.e., alignment) as an inherent limitation of the traditional approach for training a single AI model to assist human decision making. To overcome this, we introduce a novel, human-centered adaptive AI ensemble that strategically toggles between two specialist AI models—the aligned model and the complementary model—based on contextual cues, using an elegantly simple yet provably near-optimal Rational Routing Shortcut mechanism. Comprehensive theoretical analyses elucidate why the adaptive AI ensemble is effective and when it yields maximum benefits. Moreover, experiments on both simulated and real-world data show that when humans are assisted by the adaptive AI ensemble in decision making, they can achieve significantly higher performance than when they are assisted by single AI models that are trained to either optimize for its independent performance or even the human-AI team performance.

Large Language Models (LLMs) excel in reasoning and generation across domains, but still struggle with identifying and diagnosing complex errors. This stems mainly from training objectives that prioritize correct answers, limiting exposure to and learning from errors. While recent studies have begun to address this by introducing error signals, most rely on shallow, static errors, restricting improvement in deep diagnostic ability. To overcome this, we propose Hide and Seek Game (HSG), a dynamic adversarial framework for error generation and diagnosis, and evaluate it on mathematical problem-solving. HSG involves two adversarial roles: Sneaky, which hides by generating subtle, deceptive reasoning errors, and Diagnosis, which seeks to accurately detect them. Through adversarial co-evolution, both error stealth and diagnostic precision are enhanced. Experiments on three mathematical reasoning datasets demonstrate that HSG significantly boosts error diagnosis, achieving 16.8%-31.4% higher accuracy than baselines like GPT-4o. We also release a challenging dataset of deceptive errors and diagnostic annotations as a benchmark for future research.

Counterfactual regret minimization (CFR) algorithms are a foundational class of methods for solving imperfect-information games, with the time average of their iterates converging to a Nash equilibrium in two-player zero-sum games. Prior state-of-the-art variants, Discounted CFR (DCFR) and Predictive CFR+ (PCFR+), achieved the fastest known practical performance by improving convergence rates over vanilla CFR through discounting early iterations with a fixed discounting scheme. More recently, Dynamic DCFR (DDCFR) introduced agent-learned dynamic discounting schemes to further accelerate convergence, at the cost of increased complexity. To address this, we propose Hyperparameter Schedules (HSs), a remarkably simple, training-free framework that dynamically adjusts CFR discounting over time. HSs aggressively downweight early updates and gradually transition to trusting late-stage strategies, leading to substantially faster convergence with only a few lines of code modifications. We show that HSs derived from just three small extensive-form games generalize effectively to 17 diverse games (including large-scale realistic poker) in both extensive-form and normal-form settings, without any game-specific tuning. Our method establishes a new state of the art for solving two-player zero-sum games.

Computing stable partitions in hedonic games is a challenging task because there exist games in which stable outcomes do not exist. Even more, these No-instances can often be leveraged to prove computational hardness results. We make this impression rigorous in a dynamic model of cardinal hedonic games by providing meta theorems. These imply hardness of deciding about the possible or necessary convergence of deviation dynamics based on the mere existence of No-instances. Our results hold for additively separable, fractional, and modified fractional hedonic games (ASHGs, FHGs, and MFHGs). Moreover, they encompass essentially all reasonable stability notions based on single-agent deviations. In addition, we propose dynamics as a method to find individually rational and contractually individual stable (CIS) partitions in ASHGs. In particular, we find that CIS dynamics from the singleton partition possibly converge after a linear number of deviations but may require an exponential number of deviations in the worst case.

We present a polynomial-time algorithm for exactly computing second-price pacing equilibria (SPPE) in auction markets with a constant number of buyers. SPPE plays a central role in modern advertising auctions; however, computing or even approximating it is PPAD-hard in general. To overcome this computational barrier in the restricted setting, we adopt the cell-decomposition method. Specifically, we partition the solution space into polynomially many cells, each defined by hyperplanes corresponding to a fixed ordering of buyers’ scaled valuations across goods. Within each cell, the equilibrium computation reduces to solving a constant number of linear programs. Notably, our algorithm can also efficiently identify equilibria that optimize key objectives such as revenue or social welfare. To the best of our knowledge, this is the first algorithm that efficiently computes an exact SPPE for a simple and natural class of second-price pacing games.

Inequality measures such as the Gini coefficient are used to inform and motivate policymaking, and are increasingly applied to digital platforms. We analyze how measures fare in pseudonymous settings that are common in the digital age. One key challenge of such environments is the ability of actors to create fake identities under fictitious false names, also known as ``Sybils.'' While some actors may do so to preserve their privacy, we show that this can hamper inequality measurements: it is impossible for measures satisfying the literature's canonical set of desired properties to assess the inequality of an economy that may harbor Sybils. We characterize the class of all Sybil-proof measures, and prove that they must satisfy relaxed version of the aforementioned properties. Furthermore, we show that the structure imposed restricts the ability to assess inequality at a fine-grained level. We then apply our results to prove that popular measures are not Sybil-proof, with the famous Gini coefficient being but one example out of many. Finally, we examine dynamics leading to the creation of Sybils in digital and traditional settings.

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers use neural networks to approximate its behavior. However, existing methods are mainly based on vanilla CFR and struggle to effectively integrate more advanced CFR variants. In this work, we propose an efficient model-free neural CFR algorithm, overcoming the limitations of existing methods in approximating advanced CFR variants. At each iteration, it collects variance-reduced sampled advantages based on a value network, fits cumulative advantages by bootstrapping, and applies discounting and clipping operations to simulate the update mechanisms of advanced CFR variants. Experimental results show that, compared with model-free neural algorithms, it exhibits faster convergence in typical imperfect-information games and demonstrates stronger adversarial performance in a large poker game.

In knockout tournaments, players compete in successive rounds, with losers eliminated and winners advancing until a single champion remains. Given a tournament digraph D, which encodes the outcomes of all possible matches, and a designated player v* in V(D), the Tournament Fixing problem (TFP) asks whether the tournament can be scheduled in a way that guarantees v* emerges as the winner. TFP is known to be NP-hard, but is fixed-parameter tractable (FPT) when parameterized by structural measures such as the feedback arc set (fas) or feedback vertex set (fvs) number of the tournament digraph. In this paper, we introduce and study two new structural parameters: the number of players who can defeat v* (i.e., the in-degree of v*, denoted by k) and the number of players that v* can defeat (i.e., the out-degree of v*, denoted by l). A natural question is that: can TFP be efficiently solved when k or l is small? We answer this question affirmatively by showing that TFP is FPT when parameterized by either the in-degree or out-degree of v*. Our algorithm for the in-degree parameterization is particularly involved and technically intricate. Notably, the in-degree k can remain small even when other structural parameters, such as fas or fvs, are large. Hence, our results offer a new perspective and significantly broaden the parameterized algorithmic understanding of the Tournament Fixing problem.

In an online fair allocation problem, a sequence of indivisible items arrives online and needs to be allocated to offline agents immediately and irrevocably. In our paper, we study the online allocation of either goods or chores. We employ popular fairness notions, including envy-freeness up to one item (EF1) and maximin share fairness (MMS) to capture fairness, and utilitarian social welfare (USW) to measure efficiency. For both settings of items, we present a series of positive results regarding the existence of fair and efficient allocations with widely studied classes of additive binary and personalized bi-valued valuation/cost functions. Furthermore, we complement our results by constructing counterexamples to establish our results as among the best guarantees possible.

We study the fair allocation of indivisible items to groups of agents from the perspectives of both the agents and a centralized allocator. In our setting, the centralized allocator aims to ensure that the allocation is fair both among the groups and between individual agents. This setting applies to many real-world scenarios, such as when a school administrator allocates resources (e.g., office spaces and supplies) to staff members within departments or when a city council allocates limited housing units to families in need across different communities. To ensure fairness between agents, we consider the classical notion of envy-freeness (EF). To ensure fairness among groups, we introduce the notion of centralized group equitability (CGEQ), which captures fairness for groups from the centralized allocator’s perspective. Because an EF or CGEQ allocation does not always exist in general, we consider their natural relaxations: envy-freeness to one item (EF1) and centralized group equitability up to one item (CGEQ1). For different classes of valuation functions of the agents and the centralized allocator, we show that allocations satisfying both EF1 and CGEQ1 always exist, and we design efficient algorithms to compute such allocations. We also consider the centralized group maximin share (CGMMS) from the centralized allocator's perspective as a group-level fairness objective with EF1 for agents, and present several results.

Researchers strategically choose where to submit their work in order to maximize its impact, and these publication decisions in turn determine venues' impact factors. To analyze how individual publication choices both respond to and shape venue impact, we introduce a game-theoretic framework - coined the Publication Choice Problem - that captures this two‐way interplay. We show the existence of a pure-strategy equilibrium in the Publication Choice Problem and its uniqueness under binary researcher types. Our characterizations of the equilibrium properties offer insights about what publication behaviors better indicate a researcher's impact level. Through equilibrium analysis, we further investigate how labeling papers with ``spotlight'' affects the impact factor of venues in the research community. Our analysis shows that competitive venue labeling top papers with ``spotlight'' may decrease the overall impact of other venues in the community, while less competitive venues with ``spotlight'' labeling have an opposite impact.

Recent research on instant runoff voting (IRV) shows that it exhibits a striking property over unimodal one-dimensional preferences: there is an exclusion zone around the median voter such that the winner must come from the exclusion zone, unless no such candidate exists. Thus, IRV cannot elect an extreme candidate in this setting as long as a sufficiently moderate candidate runs. In this work, we examine the mathematical structure of exclusion zones as a broad phenomenon in more general preference spaces. We prove that with voters uniformly distributed over any d-dimensional hyperrectangle (for d > 1), IRV has no such exclusion zone. However, we also show that IRV exclusion zones are not solely a one-dimensional phenomenon. For irregular higher-dimensional preference spaces with fewer symmetries than hyperrectangles, IRV can have nontrivial exclusion zones. As a further exploration, we study IRV exclusion zones with graph-based preferences, where nodes represent voters who prefer candidates closer to them in the graph. Here, we show that IRV exclusion zones present a surprising computational challenge: even checking whether a given set of positions is an IRV exclusion zone is NP-hard. We develop an efficient randomized approximation algorithm for checking and finding exclusion zones in graphs. Finally, we report on computational experiments with exclusion zones: (i) performing an exhaustive computer search of small graphs and trees, we find nontrivial IRV exclusion zones in most small graphs; and (ii) applying our approximation algorithm to a collection of larger real-world school friendship networks, we find that about 60% of these networks have probable nontrivial IRV exclusion zones. While our focus is on IRV, the properties of exclusion zones we establish provide new methods for analyzing voting systems in metric spaces more generally.

A safe Pareto improvement (SPI) is a modification of a game that leaves all players better off with certainty. SPIs are typically proven under qualitative assumptions about the way different games are played. For example, we assume that strictly dominated strategies can be iteratively removed and that isomorphic games are played isomorphically. In this work, we study SPIs achieved through three types of \textit{ex post} verifiable commitments -- promises about player behavior from which deviations can be detected by observing the game. First, we consider disarmament -- commitments not to play certain actions. Next, we consider SPIs based on \textit{token games}. A token game is a game played by simply announcing an action (via cheap talk). As such, its outcome is intrinsically meaningless. However, we assume the players commit in advance to play specific (pure or correlated) strategy profiles in the original game as a function of the token game outcome. Under such commitments, the token game becomes a new, meaningful normal-form game. Finally, we consider default-conditional commitment: SPIs in settings where the players' default ways of playing the original game can be credibly revealed and hence the players can commit to act as a function of this default. We characterize the complexity of deciding whether SPIs exist in all three settings, giving a mixture of characterizations and efficient algorithms and \NP- and \textsc{Graph Isomorphism}-hardness

Cake-cutting algorithms, which aim to fairly allocate a continuous resource based on individual agent preferences, have seen significant progress over the past two decades. Much of the research has concentrated on fairness, with comparatively less attention given to other important aspects. In 2010, Chen et al. introduced an algorithm that, in addition to ensuring fairness, was strategyproof---meaning agents had no incentive to misreport their valuations. However, even in the absence of strategic incentives to misreport, agents may still hesitate to reveal their true preferences due to privacy concerns (e.g., when allocating advertising time between firms, revealing preferences could inadvertently expose planned marketing strategies or product launch timelines). In this work, we extend the strategyproof algorithm of Chen et al. by introducing a privacy-preserving dimension. To the best of our knowledge, we present the first private cake-cutting protocol, and, in addition, this protocol is also envy-free and strategyproof. Our approach replaces the algorithm’s centralized computation with a novel adaptation of cryptographic techniques, enabling privacy without compromising fairness or strategyproofness. Thus, our protocol encourages agents to report their true preferences not only because they are not incentivized to lie, but also because they are protected from having their preferences exposed.