ICML 2026 Papers

Data heterogeneity is a fundamental challenge in Federated Learning (FL), where induced model drift often results in "negative gains" for global models on data-abundant clients, with performance falling below that of local training. To address this issue, we propose FedGain, a novel framework that optimizes collaborative client clustering to mitigate the negative gain. We are the first to develop a modified Scaling Law (SL) to quantify the reduction in data utility caused by heterogeneity and define Effective Federated Capacity to align clients with the highest potential collaboration gains. Extensive experiments demonstrate that our modified SL strictly adheres to the power-law learning discipline in non-IID scenarios. FedGain effectively suppresses negative gains to a negligible level across various FL algorithms and outperforms other Clustered FL methods.

Learning from demonstration can be an effective way to teach robots task-oriented policies. However, in an interactive setting when demonstrations are limited by time or other budgetary constraints, it is challenging to find those that fix the learner's (remaining) errors. This is especially difficult for novice teachers: they may provide task-valid trajectories, often these fail to meaningfully improve the policy due to their lack of knowledge of learning mechanisms internal to the robot. This paper introduces CLASP (Collaborative Learning with Anchored State-space Partitions), which summarises the teaching process as a compact map of behavioural regions anchored in the teacher's own demonstrations. The map connects task failure to actionable changes to demonstrations by indicating what is going wrong in an intuitive way. It also enables difficulty-aware training that emphasises regions where learning is failing. Across diverse benchmarks, CLASP improves success by up to 20\% over offline and interactive baselines under the same demonstration budget, improves robustness under distribution shift by 14–20\%, and preserves behavioural diversity.

The ability to adapt to physical actions and constraints in an environment is crucial for embodied agents (e.g., robots) to effectively collaborate with humans. Such physically grounded human-AI collaboration must account for the increased complexity of the continuous state-action space and constrained dynamics caused by physical constraints. However, most existing collaboration benchmarks are discrete or do not consider physical attributes and constraints. To address this, we introduce Moving Out, a human-AI collaboration benchmark that resembles a wide range of collaboration modes affected by physical attributes and constraints, such as moving heavy items together and coordinating actions to move an item around a corner. Moving Out consists of two challenges and human-human interaction data to comprehensively evaluate models' abilities to adapt to diverse human behaviors and unseen physical attributes. To give embodied agents the capability to collaborate with humans under physical attributes and constraints, we propose a novel method, BASS (Behavior Augmentation, Simulation, and Selection), to enhance the diversity of agents and their understanding of the outcome of actions. We systematically compare BASS and state-of-the-art models in AI-AI and human-AI experiments, showing that BASS can effectively collaborate with both unseen AI and humans.

Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose \textbf{Group Cognition Learning (GCL)}, a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design.

In personalized federated learning (PFL), collaboration graphs specify model aggregation among clients. However, without constraints on the collaboration geometry, training can drift into two degenerate regimes: global consensus or spontaneous clustering. This paper provides a unified dynamical analysis: under the same budget of representative models, collaborative PFL is more expressive and achieves higher-order approximation accuracy than clustered PFL. An upper bound on disagreement further reveals two degeneration mechanisms—overly strong collaboration drives consensus (reducing to standard federated learning), while similarity-driven weight updates make the graph nearly reducible and induce self-clustering (collapsing to clustered PFL). Motivated by these findings, we propose pFedCCG. pFedCCG preserves the expressivity advantage via controlled collaboration geometry (CCG): it builds a static similarity-based collaboration template decoupled from training, optimizes a Markovian collaboration matrix with a prescribed stationary distribution via reversible parameterization and Euclidean projection, and schedules collaboration strength to avoid self-clustering. Experiments across diverse heterogeneity settings show consistent personalization gains and markedly reduced collapse and self-clustering. Code is available at https://github.com/YinHonb/pFedCCG.

Large language models (LLMs) are increasingly deployed as agents for decision-making (DM) in interactive and dynamic environments. However, since they are not originally designed for DM, recent studies show that LLMs struggle in basic online DM settings. We introduce ITERATIVE REGRET-MINIMIZATION FINE-TUNING (ITERATIVE RMFT), a post-training procedure that repeatedly distills low-regret decision trajectories into the base model. Unlike prior methods that rely on distilling known algorithms or enforcing manually designed reasoning formats, our approach leverages regret as a training signal to elicit improved decision-making behavior while incorporating model-generated reasoning in natural language. Empirically, ITERATIVE RMFT improves DM performance across models, including numerical Transformers, lightweight open-weight LLMs, and the closed-weight model GPT-4o mini, while exhibiting generalization across varying horizons, action spaces, reward processes, and natural-language-described DM scenarios. Overall, we position our approach as an initial exploration, calling for more principled and novel post-training paradigms for LLMs when it comes to addressing DM tasks.

Many high-stakes AI deployments proceed only if every stakeholder deems the system acceptable relative to their own minimum standard. With randomization over a finite menu of options, this becomes a feasibility question: does there exist a lottery over options that clears all stakeholders' acceptability bars? We study a query model where the algorithm proposes lotteries and receives only binary accept/reject feedback. We give deterministic and randomized algorithms that either find a unanimously acceptable lottery or certify infeasibility; adaptivity can avoid eliciting many stakeholders' constraints, and randomization further reduces the expected elicitation cost relative to full elicitation. We complement these upper bounds with worst-case lower bounds (in particular, linear dependence on the number of stakeholders and logarithmic dependence on precision are unavoidable). Finally, we develop learning-augmented algorithms that exploit natural forms of advice (e.g., likely binding stakeholders or a promising lottery), improving query complexity when predictions are accurate while preserving worst-case guarantees.

Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based methods, improve robustness through diversity but often lack mechanisms for efficient adaptation beyond the training distribution. Fine-tuning is also impractical for few-shot learning because it requires a large number of interactions for meaningful improvement. To address these limitations, we propose Coordination Transformers (CooT), a framework that leverages in-context learning (ICL) for real-time partner adaptation. Unlike prior ICL approaches that focus on task generalization, CooT is designed to generalize across diverse partner behaviors. Trained on trajectories from behavior-preferring agents, it learns to align actions with partner intentions purely through observation. We evaluate CooT on two challenging multi-agent benchmarks: Overcooked and Google Research Football. Results show that CooT consistently outperforms population-based methods, gradient-based fine-tuning, and Meta-RL baselines, achieving stable and rapid adaptation without parameter updates. Human evaluations also identify CooT as a preferred collaborator, and our ablations confirm its ability to adapt quickly to new partners and remain stable under sudden partner changes, making it reliable for real-world human-AI collaboration.

Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-theoretic framework that seeks to minimize the expected loss (risk) against a worst-case distribution consistent with the prediction set's coverage guarantee. We first characterize the minimax optimal policy for a fixed prediction set, showing that it balances the worst-case loss inside the set with a penalty for potential losses outside the set. Building on this, we derive the optimal prediction set construction that minimizes the resulting robust risk subject to a coverage constraint. Finally, we introduce Risk-Optimal Conformal Prediction (ROCP), a practical algorithm that targets these risk-minimizing sets while maintaining finite-sample distribution-free marginal coverage. Empirical evaluations on medical diagnosis and a toy static hazard-decision benchmark demonstrate that ROCP reduces critical mistakes compared to baselines, particularly when out-of-set errors are costly. The source code to reproduce our experiments is available at https://github.com/TaoWangPenn/Risk-Optimal-Conformal-Prediction.

Federated learning often face both data and model heterogeneity, with the latter often more challenging. Architectural differences yield incompatible representation, making the knowledge-sharing carrier central to heterogeneous collaboration. Using proxy model enables distillation-based collaboration but incurs high communication and computation costs. Prototype-based carriers are lighter yet cause semantic confusion when incompatible features are mixed. Therefore, we propose rule-based federated learning (RFL) that shares interpretable, class-discriminative rules to enable heterogeneous collaboration, avoid feature confusion, and keep communication lightweight. RFL uses a rule network to unify clients’ decision features and collaborates at the rule level, avoiding forcible averaging of incompatible representations. RFL selects sparse, high-coverage, beneficial rules for broadcasting, compressing shared knowledge into an interpretable class-rule set and reducing communication and computation costs. Each client selectively activates only rules relevant to its local classes, mitigating negative transfer while preserving personalization. Across heterogeneous settings, RFL achieves a better accuracy–communication trade-off.

Millimeter-wave (mmWave) enables privacy-preserving, illumination-robust human pose estimation (HPE), with each mmWave frame represented as a range--angle--Doppler tensor, providing spatial magnitude for localization and Doppler signatures for motion-related cues. However, existing mmWave-based HPE methods either underutilize or naïvely fuse Doppler signatures with spatial magnitude, disregarding their distinct physical semantics. As a result, non-human Doppler signatures can be misinterpreted as human motion cues, leading to jittery trajectories. We propose \textbf{PULSE}, which converts Doppler signatures into confidence-aware motion prompts and injects them into spatial magnitude reasoning through constrained interactions. By screening Doppler prompts before they influence prediction, PULSE first suppresses spurious spectral motion cues and then uses the screened prompts to stabilize prediction. Across three datasets spanning single- and multi-person settings, PULSE consistently improves pose accuracy and temporal stability, indicating that controlled Doppler prompting is a practical direction for stable mmWave HPE. Codes are available in supplementary materials.

Large language models (LLMs) are increasingly used as decision modules, yet existing benchmarks provide limited coverage of long-horizon, adversarial interaction while faithfully acting on human instructions. We introduce a long-horizon Red Alert RTS benchmark with a hierarchical interface in which LLMs output budgeted, low-frequency macro/tactical intents that are executed deterministically for standardized comparison. The benchmark evaluates (i) robustness to ``rules-as-variable'' perturbations via rule-style shifts , (ii) competitive strength via Elo-style ratings from head-to-head matches, and (iii) human steerability via standardized language interventions. Beyond win/loss, we log economy growth/spending, combat loss ratio, and visibility coverage to diagnose long-horizon failure modes. Overall, the benchmark provides a reproducible and diagnostic testbed for robustness and controllability in long-horizon adversarial decision making.

Personalizing AI decision support for heterogeneous human decision-makers remains a key challenge. We study a collaboration workflow where AI provides a reduced prediction set via conformal prediction and the human makes the final decision based on the set. We formulate this personalization problem as a contextual bandit, where individual and task features form the context, candidate significance levels $\alpha$ serve as arms, and the optimal prediction-set size varies across contexts. To address large arm spaces and high-dimensional contexts, we introduce the Adaptively Grouped Contextual Bandit (AGCB) framework, which avoids global function approximation by exploiting two Human-AI structural assumptions: continuity and monotonicity. Continuity enables information sharing across nearby contexts and decisions, and drives a data-driven Zooming Mechanism that balances intra-group estimation error against inter-group approximation bias. Monotonicity converts each observation into directional counterfactual information over the $K$ candidate $\alpha$ values, reducing the arm-dependence factor from polynomial to logarithmic in $K$. Together, these mechanisms yield minimax-optimal dependence on the learning horizon $T$ for both cumulative and simple regret objectives. Empirical results confirm that AGCB achieves the strongest overall performance across most heterogeneous, data-scarce settings.

As humans increasingly rely on multi-round conversational AI for high-stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human-centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user-defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution-free algorithm with finite-sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM-simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual-harm and complementarity violation rates even under non-stationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior.

Distributionally robust optimisation (DRO) minimises the worst-case expected loss over an ambiguity set that can capture distributional shifts in out-of-sample environments. While Huber (linear-vacuous) contamination is a classical minimal-assumption model for an $\varepsilon$-fraction of arbitrary perturbations, including it in an ambiguity set can make the worst-case risk infinite and the DRO objective vacuous unless one imposes strong boundedness or support assumptions. We address these challenges by introducing bulk-calibrated credal ambiguity sets: we learn a high-mass bulk set from data while considering contamination inside the bulk and bounding the remaining tail contribution separately. This leads to a closed-form, finite $\mathrm{mean}+\sup$ robust objective and tractable linear or second-order cone programs for common losses and bulk geometries. Through this framework, we highlight and exploit the equivalence between the imprecise probability (IP) notion of upper expectation and the worst-case risk, demonstrating how IP credal sets translate into DRO objectives with interpretable tolerance levels. Experiments on heavy-tailed inventory control, geographically shifted house-price regression, and demographically shifted text classification show competitive robustness-accuracy trade-offs and efficient optimisation times, using Bayesian, frequentist, or empirical reference distributions.

LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans nor benchmarks for LLMs, fail to capture this shift, excluding problems that require both human reasoning to guide solutions and AI efficiency for implementation. We introduce CentaurEval, a unified, ecologically valid benchmark for measuring human-in-the-loop value in coding. CentaurEval's core innovation is its "Collaboration-Necessary" problem templates, which are intractable for standalone LLMs or humans, but solvable through effective collaboration. CentaurEval dynamically instantiates tasks from 45 templates, providing a standardized IDE for humans and a reproducible 450-task toolkit for LLMs. We benchmark 45 participants against 5 LLMs under 4 levels of human intervention. Results show that while LLMs or humans alone achieve poor pass rates (0.67% and 18.89%), human–AI collaboration significantly improves to 31.11%. Our analysis reveals an emerging co-reasoning partnership, challenging the traditional human-tool hierarchy by showing that strategic breakthroughs can originate from either humans or AI.

AI predictive systems increasingly support high-stakes decision making, yet robust decisions under uncertainty often rely on human capabilities beyond AI alone. This motivates collaborative approaches that combine human judgment with AI predictions. We study this problem through the lens of uncertainty quantification and introduce **Human-AI Collaborative Uncertainty Quantification**, a framework in which an AI system refines a human expert’s proposed prediction set subject to two principles: **counterfactual harm**, requiring that the AI not degrade correct human judgments, and **complementarity**, requiring recovery of correct outcomes the human missed. At the population level, we show that the optimal collaborative prediction set has a simple two-threshold structure over a single score function, governing pruning and augmentation relative to the human proposal. Building on this characterization, we develop offline and online calibration algorithms with **distribution-free** finite-sample guarantees. The online algorithm adapts to arbitrary distribution shifts, including settings where human behavior evolves through interaction with the AI. Empirically, we show that collaborative prediction sets outperform human-only and AI-only baselines, achieving improved coverage--efficiency tradeoffs across image classification, regression, and text-based medical decision making.

Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combinatorial spaces. Traditional evolutionary algorithms often get trapped in local optima, while expert knowledge can provide crucial guidance for accelerating convergence. Large language models (LLMs) offer powerful priors and reasoning ability, making them natural optimizers when expert knowledge matters. However, closed-source LLMs, though strong in exploration, cannot update their parameters and thus cannot internalize experience. Conversely, smaller open models can be continually fine-tuned but lack broad knowledge and reasoning strength. We introduce Multi-LLM Collaborative Co-evolution (MCCE), a hybrid framework that unites a frozen closed-source LLM with a lightweight trainable model. The system maintains a trajectory memory of past search processes; the small model is progressively refined via reinforcement learning, with the two models jointly supporting and complementing each other in global exploration. Unlike model distillation, this process enhances the capabilities of both models through mutual inspiration. Experiments on multi-objective drug design benchmarks show that MCCE achieves state-of-the-art Pareto front quality and consistently outperforms baselines. These results highlight a new paradigm for enabling continual evolution in hybrid LLM systems, combining knowledge-driven exploration with experience-driven learning. The code of MCCE is available on https://github.com/lzz-z/MCCE

Reinforcement-learning problems typically define the goal as maximizing the expected value of a scalar reward function. But, pairwise preferences are often easier to specify than scalar rewards, and they express certain goals that scalar rewards cannot. Methods for reinforcement learning with pairwise preferences have thus received growing interest. Unfortunately, these methods are inefficient in problems with long time horizons, and they lack guarantees on the performance of Markov policies relative to history-dependent policies, which bridge the theory and practice of reinforcement learning. We therefore propose the *Markov decision contest* as a new problem model for reinforcement learning with pairwise preferences. We prove that stationary Markov policies are optimal among all history-dependent policies, that solving a Markov decision contest exactly is in P, and that a simple iterative algorithm converges to an optimal policy at a sublinear rate. Lastly, in a set of high-dimensional decision problems with long time horizons, we show that our approximate algorithm is significantly more learning-efficient than prior work.