ICML 2025 论文列表

We address the problem of interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters, we create a novel dataset of sequential preferences, which we leverage, together with large-scale open-source (non-sequential) datasets. We construct user-preference and user-choice models using an EM strategy and identify varying user preference types. We then leverage a large multimodal language model (LMM) and a value-based RL approach to suggest an adaptive and diverse slate of prompt expansions to the user. Our Preference Adaptive and Sequential Text-to-image Agent (PASTA) extends T2I models with adaptive multi-turn capabilities, fostering collaborative co-creation and addressing uncertainty or underspecification in a user's intent. We evaluate PASTA using human raters, showing significant improvement compared to baseline methods. We also open-source our sequential rater dataset and simulated user-rater interactions to support future research in user-centric multi-turn T2I systems.

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One major challenge of RLHF is the inaccuracy of the intermediate reward model, especially in the tasks that requires complex reasoning for the reward model to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve the signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtering strategy, we use the coefficient of determination ($R^2$) between the rewards and actual scores on filtered samples as the metrics to help us find promising strategies since it measures how well the rewards filtered by PF-PPO indicate real performance. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks. In code generation, PF-PPO achieves the state-of-the-art performance of 7-billion-parameter models on HumanEval (+7.9%), MBPP (+0.7%), and LeetCode Contest (+10.0%) which is a more challenging benchmark created by us. In math reasoning, PF-PPO yields performance increase using different reward models and benchmarks (Ape210K and CMATH).

Estimating the unknown reward functions driving agents' behavior is a central challenge in inverse games and reinforcement learning. This paper introduces a unified framework for reward function recovery in two-player zero-sum matrix games and Markov games with entropy regularization. Given observed player strategies and actions, we aim to reconstruct the underlying reward functions. This task is challenging due to the inherent ambiguity of inverse problems, the non-uniqueness of feasible rewards, and limited observational data coverage. To address these challenges, we establish reward function identifiability using the quantal response equilibrium (QRE) under linear assumptions. Building on this theoretical foundation, we propose an algorithm to learn reward from observed actions, designed to capture all plausible reward parameters by constructing confidence sets. Our algorithm works in both static and dynamic settings and is adaptable to incorporate other methods, such as Maximum Likelihood Estimation (MLE). We provide strong theoretical guarantees for the reliability and sample-efficiency of our algorithm. Empirical results demonstrate the framework’s effectiveness in accurately recovering reward functions across various scenarios, offering new insights into decision-making in competitive environments.

Policy tree search is a family of tree search algorithms that use a policy to guide the search. These algorithms provide guarantees on the number of expansions required to solve a given problem that are based on the quality of the policy. While these algorithms have shown promising results, the process in which they are trained requires complete solution trajectories to train the policy. Search trajectories are obtained during a trial-and-error search process. When the training problem instances are hard, learning can be prohibitively costly, especially when starting from a randomly initialized policy. As a result, search samples are wasted in failed attempts to solve these hard instances. This paper introduces a novel method for learning subgoal-based policies for policy tree search algorithms. The subgoals and policies conditioned on subgoals are learned from the trees that the search expands while attempting to solve problems, including the search trees of failed attempts. We empirically show that our policy formulation and training method improve the sample efficiency of learning a policy and heuristic function in this online setting.

Deep reinforcement learning (RL) is effective for decision-making and control tasks like autonomous driving and embodied AI. However, RL policies often suffer from the action fluctuation problem in real-world applications, resulting in severe actuator wear, safety risk, and performance degradation. This paper identifies the two fundamental causes of action fluctuation: observation noise and policy non-smoothness. We propose LipsNet++, a novel policy network with Fourier filter layer and Lipschitz controller layer to separately address both causes. The filter layer incorporates a trainable filter matrix that automatically extracts important frequencies while suppressing noise frequencies in the observations. The controller layer introduces a Jacobian regularization technique to achieve a low Lipschitz constant, ensuring smooth fitting of a policy function. These two layers function analogously to the filter and controller in classical control theory, suggesting that filtering and control capabilities can be seamlessly integrated into a single policy network. Both simulated and real-world experiments demonstrate that LipsNet++ achieves the state-of-the-art noise robustness and action smoothness. The code and videos are publicly available at https://xjsong99.github.io/LipsNet_v2.

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL is a tricky problem, due to the iterative nature of the action generation process. We address this challenge by training an expressive one-step policy with RL, rather than directly guiding an iterative flow policy to maximize values. This way, we can completely avoid unstable recursive backpropagation, eliminate costly iterative action generation at test time, yet still mostly maintain expressivity. We experimentally show that FQL leads to strong performance across 73 challenging state- and pixel-based OGBench and D4RL tasks in offline RL and offline-to-online RL.

Parameter-sharing (PS) techniques have been widely adopted in cooperative Multi-Agent Reinforcement Learning (MARL). In PS, all the agents share a policy network with identical parameters, which enjoys good sample efficiency. However, PS could lead to homogeneous policies that limit MARL performance. We tackle this problem from the angle of gradient conflict among agents. We find that the existence of futile neurons whose update is canceled out by gradient conflicts among agents leads to poor learning efficiency and diversity. To address this deficiency, we propose GradPS, a gradient-based PS method. It dynamically creates multiple clones for each futile neuron. For each clone, a group of agents with low gradient-conflict shares the neuron's parameters. Our method can enjoy good sample efficiency by sharing the gradients among agents of the same clone neuron. Moreover, it can encourage diverse behaviors through independently updating an exclusive clone neuron. Through extensive experiments, we show that GradPS can learn diverse policies with promising performance. The source code for GradPS is available in \url{https://github.com/xmu-rl-3dv/GradPS}.

Deep reinforcement learning (DRL) has been widely used for dynamic algorithm configuration, particularly in evolutionary computation, which benefits from the adaptive update of parameters during the algorithmic execution. However, applying DRL to algorithm configuration for multi-objective combinatorial optimization (MOCO) problems remains relatively unexplored. This paper presents a novel graph neural network (GNN) based DRL to configure multi-objective evolutionary algorithms. We model the dynamic algorithm configuration as a Markov decision process, representing the convergence of solutions in the objective space by a graph, with their embeddings learned by a GNN to enhance the state representation. Experiments on diverse MOCO challenges indicate that our method outperforms traditional and DRL-based algorithm configuration methods in terms of efficacy and adaptability. It also exhibits advantageous generalizability across objective types and problem sizes, and applicability to different evolutionary computation methods.

Navigating in an unfamiliar environment during deployment poses a critical challenge for a vision-language navigation (VLN) agent. Yet, test-time adaptation (TTA) remains relatively underexplored in robotic navigation, leading us to the fundamental question: what are the key properties of TTA for online VLN? In our view, effective adaptation requires three qualities: 1) flexibility in handling different navigation outcomes, 2) interactivity with external environment, and 3) maintaining a harmony between plasticity and stability. To address this, we introduce FeedTTA, a novel TTA framework for online VLN utilizing feedback-based reinforcement learning. Specifically, FeedTTA learns by maximizing binary episodic feedback, a practical setup in which the agent receives a binary scalar after each episode that indicates the success or failure of the navigation. Additionally, we propose a gradient regularization technique that leverages the binary structure of FeedTTA to achieve a balance between plasticity and stability during adaptation. Our extensive experiments on challenging VLN benchmarks demonstrate the superior adaptability of FeedTTA, even outperforming the state-of-the-art offline training methods in REVERIE benchmark with a single stream of learning.

Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges like misinformation, hallucinations, bias and misuse. While existing Reinforcement Learning (RL)-based alignment methods are notoriously complex, direct optimization approaches offer a simpler alternative. In this work, we introduce a novel direct optimization approach for LLM alignment by drawing on established Information Retrieval (IR) principles. We present a systematic framework that bridges LLM alignment and IR methodologies, mapping LLM generation and reward models to IR's retriever-reranker paradigm. Building on this foundation, we propose LLM Alignment as Retriever Preference Optimization (LarPO), a new alignment method that enhances overall alignment quality. Extensive experiments validate LarPO's effectiveness with 38.9 % and 13.7 % averaged improvement on AlpacaEval2 and MixEval-Hard respectively. Our work opens new avenues for advancing LLM alignment by integrating IR foundations, offering a promising direction for future research.

We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models. Unlike the existing learn-then-test (LTT) technique, which relies on conventional p-value-based multiple hypothesis testing (MHT), aLTT implements sequential data-dependent MHT with early termination by leveraging e-processes. As a result, aLTT can reduce the number of testing rounds, making it particularly well-suited for scenarios in which testing is costly or presents safety risks. Apart from maintaining statistical validity, in applications such as online policy selection for offline reinforcement learning and prompt engineering, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.

Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast combinatorial action spaces, leading to inefficiency. In this paper, we propose **Preference Optimization**, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling, emphasizing the superiority among sampled solutions. Methodologically, by reparameterizing the reward function in terms of policy and utilizing preference models, we formulate an entropy-regularized RL objective that aligns the policy directly with preferences while avoiding intractable computations. Furthermore, we integrate local search techniques into the fine-tuning rather than post-process to generate high-quality preference pairs, helping the policy escape local optima. Empirical results on various benchmarks, such as the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP) and the Flexible Flow Shop Problem (FFSP), demonstrate that our method significantly outperforms existing RL algorithms, achieving superior convergence efficiency and solution quality.

Solving various types of vehicle routing problems (VRPs) using a unified neural solver has garnered significant attentions in recent years. Despite their effectiveness, existing neural multi-task solvers often fail to account for the geometric structures inherent in different tasks, which may result in suboptimal performance. To address this limitation, we propose a curvature-aware pre-training framework. Specifically, we leverage mixed-curvature spaces during the feature fusion stage, encouraging the model to capture the underlying geometric properties of each instance. Through extensive experiments, we evaluate the proposed pre-training strategy on existing neural multi-task solvers across a variety of testing scenarios. The results demonstrate that the curvature-aware pre-training approach not only enhances the generalization capabilities of existing neural VRP solvers on synthetic datasets but also improves solution quality on real-world benchmarks.

We develop a semi-amortized, policy-based, approach to Bayesian experimental design (BED) called Stepwise Deep Adaptive Design (Step-DAD). Like existing, fully amortized, policy-based BED approaches, Step-DAD trains a design policy upfront before the experiment. However, rather than keeping this policy fixed, Step-DAD periodically updates it as data is gathered, refining it to the particular experimental instance. This test-time adaptation improves both the flexibility and the robustness of the design strategy compared with existing approaches. Empirically, Step-DAD consistently demonstrates superior decision-making and robustness compared with current state-of-the-art BED methods.

Cooperative Multi-Agent Reinforcement Learning (MARL) has become a critical tool for addressing complex real-world problems. However, off-policy MARL methods, which rely on joint Q-functions, face significant scalability challenges due to the exponentially growing joint action space. In this work, we highlight a critical yet often overlooked issue: erroneous Q-target estimation, primarily caused by extrapolation error. Our analysis reveals that this error becomes increasingly severe as the number of agents grows, leading to unique challenges in MARL due to its expansive joint action space and the decentralized execution paradigm. To address these challenges, we propose a suite of techniques tailored for off-policy MARL, including annealed multi-step bootstrapping, averaged Q-targets, and restricted action representation. Experimental results demonstrate that these methods effectively mitigate erroneous estimations, yielding substantial performance improvements in challenging benchmarks such as SMAC, SMACv2, and Google Research Football.

In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered access to the deployment environment for the full lifetime of the agent. For example, agent designers select the best performing hyperparameters in Atari by testing each for 200 million frames and then reporting results on 200 million frames. In this position paper, we argue and demonstrate the pitfalls of this inappropriate empirical methodology: lifetime tuning. We provide empirical evidence to support our position by testing DQN and SAC across several of continuing and non-stationary environments with two main findings: (1) lifetime tuning does not allow us to identify algorithms that work well for continual learning---all algorithms equally succeed; (2) recently developed continual RL algorithms outperform standard non-continual algorithms when tuning is limited to a fraction of the agent's lifetime. The goal of this paper is to provide an explanation for why recent progress in continual RL has been mixed and motivate the development of empirical practices that better match the goals of continual RL.

High-frequency control in continuous action and state spaces is essential for practical applications in the physical world. Directly applying end-to-end reinforcement learning to high-frequency control tasks struggles with assigning credit to actions across long temporal horizons, compounded by the difficulty of efficient exploration. The alternative, learning low-frequency policies that guide higher-frequency controllers (e.g., proportional-derivative (PD) controllers), can result in a limited total expressiveness of the combined control system, hindering overall performance. We introduce *EvoControl*, a novel bi-level policy learning framework for learning both a slow high-level policy (using PPO) and a fast low-level policy (using Evolution Strategies) for solving continuous control tasks. Learning with Evolution Strategies for the lower-policy allows robust learning for long horizons that crucially arise when operating at higher frequencies. This enables *EvoControl* to learn to control interactions at a high frequency, benefitting from more efficient exploration and credit assignment than direct high-frequency torque control without the need to hand-tune PD parameters. We empirically demonstrate that *EvoControl* can achieve a higher evaluation reward for continuous-control tasks compared to existing approaches, specifically excelling in tasks where high-frequency control is needed, such as those requiring safety-critical fast reactions.

Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level objectives. Existing methods either rely on short-term auto-regressive action generation or face limitations in accurately simulating rollouts and assessing outcomes, leading to sub-optimal decisions. This paper introduces a novel LLM-based Actor-Critic framework, termed LAC, that effectively improves LLM policies with long-term action evaluations in a principled and scalable way. Our approach addresses two key challenges: (1) extracting robust action evaluations by computing Q-values via token logits associated with positive/negative outcomes, enhanced by future trajectory rollouts and reasoning; and (2) enabling efficient policy improvement through a gradient-free mechanism. Experiments across diverse environments -- including high-level decision-making (ALFWorld), low-level action spaces (BabyAI-Text), and large action spaces (WebShop) -- demonstrate the framework’s generality and superiority over state-of-the-art methods. Notably, our approach achieves competitive performance using 7B/8B parameter LLMs, even outperforming baseline methods employing GPT-4 in complex tasks. These results underscore the potential of integrating structured policy optimization with LLMs’ intrinsic knowledge to advance decision-making capabilities in multi-step environments.

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer architecture, which results in powerful agents. However, due to slow inference times, Transformer-based approaches are impractical for real-time applications, such as robotics. Recently, modern recurrent architectures, such as xLSTM and Mamba, have been proposed that exhibit parallelization benefits during training similar to the Transformer architecture while offering fast inference. In this work, we study the aptitude of these modern recurrent architectures for large action models. Consequently, we propose a Large Recurrent Action Model (LRAM) with an xLSTM at its core that comes with linear-time inference complexity and natural sequence length extrapolation abilities. Experiments on 432 tasks from 6 domains show that LRAM compares favorably to Transformers in terms of performance and speed.