论文检索

Deep Learning · Large Language Models

Jiaqi Liu, Yaofeng Su, Peng Xia, Siwei Han, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which distills unstructured interactions into compact, multi-view indexed memory units; (2) Online Semantic Synthesis, an intra-session process that instantly integrates related context into unified abstract representations to eliminate redundancy; and (3) Intent-Aware Retrieval Planning, which infers search intent to dynamically determine retrieval scope and construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% in LoCoMo while reducing inference-time token consumption by up to 30×, demonstrating a superior balance between performance and efficiency.

Reinforcement Learning · Deep RL

Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko, Benjamin Eysenbach

How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a language to answer these questions formally. Empirically, deep RL policies are often parameterized as neural networks with static architectures, conflating the amount of compute and the number of parameters. In this paper, we formalize compute bounded policies and prove that policies which use more compute can solve problems and generalize to longer-horizon tasks that are outside the scope of policies with less compute. Building on prior work in algorithmic learning and model-free planning, we propose a minimal architecture that can use a variable amount of compute. Our experiments complement our theory. On a set 31 different tasks spanning online and offline RL, we show that $(1)$ this architecture achieves stronger performance simply by using more compute, and $(2)$ stronger generalization on longer-horizon test tasks compared to standard feedforward networks or deep residual network using upto 5 times more parameters.

Reinforcement Learning · Batch/Offline

Jinu Hyeon, Woobin Park, Hongjoon Ahn, Taesup Moon

Hierarchical policies in offline goal-conditioned reinforcement learning (GCRL) addresses long-horizon tasks by decomposing control into high-level subgoal planning and low-level action execution. A critical design choice in such architectures is the goal representation—the compressed encoding of goals that serves as the interface between these levels. Existing approaches commonly derive goal representations while learning value functions, implicitly assuming that preserving information sufficient for value estimation is adequate for optimal control. We show that this assumption can fail, even when the value estimation is exact, as such representations may collapse goal states that need to be differentiated for action learning. To address this, we introduce an information-theoretic framework that defines *action sufficiency*, a condition on goal representations necessary for optimal action selection. We prove that value sufficiency does not imply action sufficiency and empirically verify that the latter is more strongly associated with control success in a discrete environment. We further demonstrate that standard log-loss training of low-level policies naturally induces action-sufficient representations. Our experimental results a popular benchmark demonstrate that our actor-derived representations consistently outperform representations learned via value estimation.

Deep Learning · Other Representation Learning

Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero, Tim G. J. Rudner, Yann LeCun, Mengye Ren

Learning good representations is essential for latent planning with world models. While pretrained visual encoders provide strong visual features, they are not tailored to planning and contain substantial information which is irrelevant to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening for representation learning in latent planning. We add a lightweight projector on top of a pretrained visual encoder to map to a lower-dimensional space, trained with a curvature regularizer that encourages locally straightened latent trajectories. We show that reducing curvature improves the conditioning of the planning objective, making gradient-based planning more stable and yielding significantly higher success rates across four goal-reaching tasks.

John Sweeney

Sequential fine-tuning on multiple datasets is ubiquitous, but the training order of sources can measurably change downstream performance; testing both orders roughly doubles compute. We model a single gradient step on a dataset as a nonlinear operator and show that non-commutativity induces order-dependent effects governed by a commutator (Lie-bracket) term. For two sources $A,B$ and target domain $E$, this yields a directional score $\sigma_{AB}^{(E)} = \langle g_E, H_B g_A - H_A g_B \rangle$ that predicts whether $A \to B$ or $B \to A$ yields lower $L_E$. We evaluate $g_E$ at a reference point capturing the shared drift of both orders (Trotter scoring) and develop a theory-driven $\eta$-autopilot that selects step sizes from pilot data by balancing signal-to-noise against higher-order stability constraints. On four LLMs and a diffusion UNet, our planner achieves 81–94% overall sign accuracy and 82–100% on highest-impact decisions, enabling practical transfer-order planning without manual hyperparameter tuning.

Jianke Zhang, Yucheng Hu, Yanjiang Guo, Xiaoyu Chen, Yichen Liu, Wenna Chen, Chaochao Lu, Jianyu Chen

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension and generation through large-scale pretraining. We posit that robotic policy learning can likewise benefit from the combined strengths of understanding, planning and continuous future representation learning. Building on this insight, we introduce UniCoD, which acquires the ability to dynamically model high-dimensional visual features through pretraining on over 1M internet-scale instructional manipulation videos. Subsequently, UniCoD is fine-tuned on data collected from the robot embodiment, enabling the learning of mappings from predictive representations to action tokens. Extensive experiments show our approach consistently outperforms baseline methods in terms of 9\% and 12\% across simulation environments and real-world out-of-distribution tasks.

Probabilistic Methods · Bayesian Models and Methods

Yujia Guo, Daolang Huang, Xinyu Zhang, Sammie Katt, Samuel Kaski, Ayush Bharti

Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are unable to adapt to dynamic constraints inherent in real-world tasks due to budget limitations, varying costs, or physical constraints that restrict how designs evolve over time. In this paper, we introduce a novel approach to BED that enables constrained optimization of experimental designs by combining offline pre-training of an amortized policy and a posterior network with online multi-step lookahead planning using scenario trees. We empirically demonstrate that our method yields substantially more informative design sequences than existing methods across a range of constrained BED tasks, while incurring only a modest additional computational overhead.

Theory · Reinforcement Learning and Planning

Sreejeet Maity, Aritra Mitra

We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the Q-learning algorithm and analyze it under the challenging asynchronous sampling model with time-correlated data. Despite corruption, we prove that the finite-time guarantees of our approach match existing bounds, up to an additive term that scales with the fraction of corrupted samples. We also establish an information-theoretic lower bound, revealing that our guarantees are near-optimal. Notably, our algorithm is agnostic to the underlying reward distribution and provides the first finite-time robustness guarantees for asynchronous Q-learning. A key element of our analysis is a refined Azuma-Hoeffding inequality for almost-martingales, which may have broader applicability in the study of RL algorithms.

Deep Learning · Large Language Models

G M Shahariar, Erfan Shayegani, Ali Nazari, Nael Abu-Ghazaleh

Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reasoning trajectories are not well understood and can lead to inconsistencies and reasoning pathologies. In this work, we propose to approximate LRM's emerging hierarchical reasoning dynamics as a trajectory within a Finite State Machine (FSM) transitioning among six abstract cognitive states. We demonstrate that these states and transitions can be captured in the latent state of the model. We believe that this representation can have different applications in the interpretability and optimization of LRM models. For example, by analyzing the topology of these transitions, we identify statistical shifts in reasoning strategies that help identify effective reasoning chains from those that fail. To illustrate these potential advantages, we propose $Q$-Value guided steering, a training-free inference-time control method that treats reasoning as a planning problem. We estimate the long-horizon utility of state transitions and apply sparse, orthogonal activation steering at sentence boundaries to align the CoT generation with optimal reasoning policies. Experiments across four benchmarks (AIME25, MATH-500, GSM8k, and GPQA Diamond) using three state-of-the-art open reasoning models demonstrate that $Q$-Value steering policy achieves significant performance gains with "surgical'' efficiency, often requiring $25\times$ fewer interventions than greedy and weighted baselines, which suggests that reasoning can be effectively controlled by guiding high-level cognitive dynamics rather than micro-managing token generation.

Reinforcement Learning · Multi-agent

Qinhong Zhou, Chuang Gan, Anoop Cherian

Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years. However, existing large language model (LLM)–based agents often exhibit behaviors that are misaligned with their partners or inconsistent with the environment state, leading to inefficient cooperation and poor task success. To address this challenge, we propose a novel framework, Learning Laws for Cooperation (LLawCo), that enables embodied agents to autonomously align with both their partners and task objectives. Our framework allows agents to reflect on past failures to extract misaligned behavioral patterns, which are used to derive high-level behavioral laws (e.g., “Talk when necessary”, “Wait for partner”). These laws are explicitly incorporated into the agents’ chains of thought via supervised fine-tuning, aligning their reasoning with task requirements and the behavior of other agents. To evaluate our approach, we introduce PARTNR-Dialog, a large-scale multi-agent communicative and cooperative planning benchmark built on the PARTNR environment. Experiments on existing tasks and our new benchmark demonstrate significant improvements in cooperative efficiency and task success rates. Across four backbone LLMs, our method achieves average success rate improvements of 4.5% on the PARTNR-Dialog benchmark and 6.8% on the TDW-MAT benchmark over state-of-the-art open-source communicative agent frameworks.

Theory · Reinforcement Learning and Planning

David Bossens, Atsushi Nitanda

Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under epistemic uncertainty. This paper presents mirror descent policy optimisation for robust constrained Markov decision processes, making use of policy gradient techniques to optimise both the policy (as a maximiser) and the transition kernel (as an adversarial minimiser) on the Lagrangian representing a constrained Markov decision process. Our proposed algorithm obtains an $\tilde{\mathcal{O}}\left(1/T^{1/3}\right)$ convergence rate in the sample-based robust constrained Markov decision process setting. The paper also contributes an algorithm for approximate gradient descent in the space of transition kernels, which is of independent interest for designing adversarial environments in general Markov decision processes. Experiments confirm the benefits of mirror descent policy optimisation in constrained and unconstrained optimisation, and significant improvements are observed in robustness tests when compared to baseline policy optimisation algorithms.

Reinforcement Learning · Planning

Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou, Charles Fleming, Zhaoran Wang, Alfredo Garcia, Mingyi Hong

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful feedback. Most existing reinforcement learning (RL) methods model LLM agents as *flat* policies operating at a single time scale, selecting an action at each turn. In sparse-reward settings, this forces the agent to infer long-range dependencies solely from distant end-of-trajectory signals, often leading to inefficient learning and unstable behavior in complex environments. We propose **HiPER**, a novel **Hi**erarchical **P**lan–**E**xecute **R**L framework that jointly models and optimizes high-level subgoal planning and low-level action execution for LLM agents to overcome flat RL's brittle long-horizon behavior and weak credit assignment under sparse outcome feedback. By maintaining persistent subgoals across multiple turns and explicitly deciding when to switch between them, HiPER introduces structured intermediate decision points that facilitate learning under sparse feedback, converting implicit multi-turn structure into learnable decisions at different time scales. To enable effective training, we introduce Hierarchical Advantage Estimation (HAE), a two-timescale policy gradient method that assigns credit to both action execution and subgoal transitions and achieves variance reduction relative to flat advantage estimation. Empirically, HiPER achieves state-of-the-art performance on challenging interactive benchmarks, reaching 97.4\% success on ALFWorld (+6.6\% over the best prior method) and 83.3\% on WebShop, with especially large gains on long-horizon tasks requiring multiple dependent subtasks. These results highlight the importance of explicit hierarchical decomposition for scalable RL training of multi-turn LLM agents.

Social Aspects · Accountability, Transparency, and Interpretability

Zehao Wang, shilong jin, Zhao Cao, Lanjun Wang

LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike execution errors, epistemic miscalibration is latent during planning, as generated plans can remain self-consistent and executable without observable errors; the miscalibration is also dynamic, as new information can alter feasibility assessments, potentially obscuring past miscalibration signals and causing them to recur over time. To address this, we propose the Epistemic Planning Calibration Agentic Workflow (EPC-AW), which assesses whether plans remain supported under varying information conditions rather than directly verifying feasibility. EPC-AW employs Information-consistency-based Plan Selection, selecting plans whose evaluations are stable across agents, together with Consistency-guided Epistemic State Refinement to adapt calibration over time by leveraging past discrepancies to guide future planning. Experiments show that EPC-AW improves system-level success by an average of 9.75\%.

Applications · Everything Else

shilong jin, Lanjun Wang, Zhuosheng Zhang

Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail to adapt to dynamic environments. To address these limitations, this work proposes the Self-Evolving GUI Agent (SE-GA), a novel framework that integrates hierarchical memory structures with an iterative self-improvement mechanism. At the core of our approach is Test-Time Memory Extension (TTME), which facilitates long-term planning by dynamically retrieving episodic, semantic, and experiential memories to provide salient contexts during inference. To ensure continuous learning, we introduce Memory-Augmented Self-Evolution (MASE), which is a training pipeline that adopts the data collected by TTME to stabilize and enhance the agent's foundational policy. Extensive evaluations across both offline and online benchmarks demonstrate SE-GA achieves state-of-the-art performance, reaching success rates of 89.0\% on ScreenSpot and 75.8\% on the challenging AndroidControl-High dataset. Furthermore, significant improvements on the AndroidWorld benchmark highlight the superior generalization to dynamic environments.

Applications · Language, Speech and Dialog

Xuhui Zhou, Valerie Chen, Zhiruo Wang, Graham Neubig, Maarten Sap, Xingyao Wang

Recent advances in coding agents have made them capable of planning, editing, running, and testing complex code bases. Despite their growing ability in coding tasks, these systems still struggle to infer and track user intent, especially when instructions are underspecified or context-dependent. To bridge this gap, we introduce ToM-SWE, a dual-agent architecture that pairs a primary software-engineering (SWE) agent with a lightweight theory-of-mind (ToM) partner agent dedicated to modeling the user's mental state. The ToM agent infers user goals, constraints, and preferences from instructions and interaction history, maintains a persistent memory of the user, and provides user-related suggestions to the SWE agent, while preserving privacy and minimizing context window load. In two software engineering benchmarks (ambiguous SWE-bench and stateful SWE-bench), ToM-SWE improves task success rates and user satisfaction. Notably, on the stateful SWE benchmark, a newly introduced evaluation that provides agents with a user simulator along with previous interaction histories, ToM-SWE achieves a substantially higher task success rate of 59.7% compared to 18.1% for OpenHands, a state-of-the-art SWE agent. Furthermore, in a three-week study with professional developers using ToM-SWE in their daily work, participants found it better aligned with their intent and useful 86% of the time, underscoring the value of stateful user modeling for practical coding agents.

General Machine Learning · Methodology

Yundaichuan Zhan, Minghe Gao, Zhongqi Yue, Wendong Bu, Wenqiao Zhang, Guoming Wang, Jisheng Dang, Juncheng Li, Siliang Tang, Yueting Zhuang

Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problem to generate long-horizon plans for complex embodied tasks. However, in open-ended environments, these symbolic representations obtained from perception are often incomplete, leading to suboptimal performance. To address this, we introduce SCOPE, a self-adaptive symbolic planning framework that supports refining action plans and evolving the symbolic world—the symbolic representations of open-ended environments. SCOPE comprises two synergistic modules: a Symbolic Execution Simulator (SESim) that conducts symbolic validation and real execution of action plans, leveraging the feedback to refine the plans and evolve the symbolic world; and a Self-Adaptive Symbolic Memory (SASMem) that further distills feedback into evolving symbolic knowledge to enhance long-horizon planning and modeling of the symbolic world. Experiments in open-ended environments show that SCOPE significantly improves the completeness of the symbolic world, the success rate of plans under environment perturbations, and cross-task grounding and adaptability across diverse embodied scenarios.

Deep Learning · Large Language Models

Chenchen Tan, Xinghao Li, Shujie Cui, Youyang Qu, Cunjian Chen, Longxiang Gao

As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy and governance requirements. This motivates selective unlearning, which suppresses information about a particular entity or topic while preserving the LLM’s general utility. However, most existing LLM unlearning methods require access to the original training corpus and rely on output-level refusal tuning or broad gradient updates, creating a tension among unlearning strength, non-target preservation, and data availability. We propose Geometric Unlearning (GU), an approach that operates directly on the model’s prompt-time planning states without access to the original training corpus. GU distills a compact, low-rank geometry of desired safe behavior from a small set of safe reference prompts, and uses lightweight anchor-in-context synthetic prompts to trigger localized, projection-based alignment of hidden planning representations to this safe geometry. A teacher-distillation regularizer on synthetic non-target anchors further reduces collateral drift. Across privacy-oriented unlearning benchmarks (ToFU and UnlearnPII), GU achieves strong target suppression with minimal impact on non-target performance, demonstrating that effective unlearning can be achieved with minimal synthetic data.

Applications · Computer Vision

Wentao Mo, Yang Liu

Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification. We introduce APEIRIA, a neuro-symbolic 3D MLLM that bridges these paradigms by distilling symbolic reasoning patterns into MLLMs with natural language chain-of-thought (CoT). Our three-stage curriculum progressively builds reasoning capabilities: (1) 3D perception alignment that grounds object visual-geometric features to the LLM's textual embedding space, (2) CoT-SFT that teaches systematic query decomposition and stepwise spatial verification from symbolic program traces, and (3) CoT-RL that extends learned reasoning patterns to open-set concepts and deeply nested instructions. This transfers reasoning patterns rather than concept-specific knowledge, preserving key NS3D virtues: transparent reasoning traces and modular interchangeability of planning and perception components. Extensive evaluations demonstrate that APEIRIA surpasses previous NS3D methods and matches state-of-the-art 3D MLLMs on 3D spatial reasoning benchmarks, presenting a unified framework combining the systematic reasoning of symbolic methods with the flexibility of modern LLMs.

Theory · Reinforcement Learning and Planning

Yivan Zhang, Ziyan Luo, Manuel Baltieri

State abstraction plays a central role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been proposed in reinforcement learning, including value functions, invariants, bisimulation relations, and behavioral metrics. However, a general principle for determining what structures are provably preserved under state abstraction is still lacking. In this paper, we present a unified framework for defining and analyzing behavioral structures in reinforcement learning. Our framework provides a compositional way to specify behavioral semantics and metrics based on local, one-step descriptions of system dynamics. Using this framework, we establish results showing how behavioral structures can be safely transferred between abstract and concrete systems. We further show how to construct quantitative metrics from logical behavioral semantics with soundness guarantees. Together, these results provide a principled foundation for reasoning about behaviors under state abstraction in reinforcement learning and offer reusable definition and proof principles for a broad class of behavioral structures in reinforcement learning.

Probabilistic Methods · Monte Carlo and Sampling Methods

Michael Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus, T. Konstantin Rusch

Low-discrepancy points are designed to efficiently fill the space in a uniform manner. This uniformity is highly advantageous in many problems in science and engineering, including in numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation. Whereas most previous low-discrepancy constructions rely on abstract algebra and number theory, Message-Passing Monte Carlo (MPMC) was recently introduced to exploit machine learning methods for generating point sets with lower discrepancy than previously possible. However, MPMC is limited to generating point sets and cannot be extended to low-discrepancy sequences (LDS), i.e., sequences of points in which every prefix has low discrepancy, a property essential for many applications. To address this limitation, we introduce Neural Low-Discrepancy Sequences *NeuroLDS*, the first machine learning-based framework for generating LDS. Drawing inspiration from classical LDS, we train a neural network to map indices to points such that the resulting sequences exhibit minimal discrepancy across all prefixes. To this end, we deploy a two-stage learning process: supervised approximation of classical constructions followed by unsupervised fine-tuning to minimize prefix discrepancies. We demonstrate that *NeuroLDS* outperforms all previous LDS constructions by a significant margin with respect to discrepancy measures. Moreover, we demonstrate the effectiveness of *NeuroLDS* across diverse applications, including numerical integration, robot motion planning, and scientific machine learning. These results highlight the promise and broad significance of Neural Low-Discrepancy Sequences.