paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models

Yuwen Wang, Tian-Hao Zhang, Minghao Cai, Yilin Ren, Ziyang Jiang, Xin Wang, Zhichao Wang, Pan Zhou, Kun Zhan, Xinyuan Qian

Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rather than answer directly from a fixed audio input. We study such problems as tool-interactive audio reasoning and develop SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools. To support this capability, we construct HIU-Corpus, comprising 65,492 interaction trajectories and 507.6 hours of audio across 24 tasks, 8 skills and 9 tools. SpeechAgent-R first learns structured interaction behaviors through trajectory-based supervised fine-tuning and then improves its decisions through multi-turn reinforcement learning. We further introduce HIU-Bench to jointly evaluate task performance, interaction quality and generalization to diverse task settings. It contains 1,395 samples across 56 tasks, including in-distribution (ID) and out-of-distribution (OOD) splits with substantial shifts in tool usage and workflow composition. SpeechAgent-R achieves 84.17 on ID tasks and 70.94 on OOD tasks, improving over the base model under the same agent harness by 15.40 and 14.23 points. These results demonstrate that learning skill and tool coordination improves audio agents' ability to handle diverse task settings and adaptive tool interactions.

arXiv

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

Xiaofeng Shi, Xiaosong Qiu, Wenxin Ma, Qian Kou, Yiming Pan, Longbin Yu, Ying Liu, Haiping Wang, Hua Zhou

Enterprise question answering requires models to acquire proprietary knowledge without discarding general capabilities. We present Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data replay, and applies reinforcement learning to residual errors. On the 707-question WnuanBench, the primary 32B route raises acceptable-answer rate (AAR) from 52.76% before adaptation to 80.06% after SFT and 91.51% after RL. Under a matched 100-update protocol, residual-error sampling outperforms full-pool and size-matched random sampling by 3.11 and 2.97 points, respectively. Source-cluster bootstrap intervals remain above zero for both contrasts, and a same-domain validation set preserves the ordering. The general-benchmark average decreases by 5.17 points across the route, concentrated in instruction following. The automatic evaluation ensemble agrees with an authoritative domain expert on 90.5% of a stratified Wnuan-Inst response sample. These results characterize both the gains and the general-capability cost of staged enterprise adaptation.

arXiv

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

Gaytri Jena, Kapil Wanaskar, Vinija Jain, Aman Chadha, Vasu Sharma, Amitava Das

Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey organises the field around that axis of weights versus skills. Its central analytical contribution is a deep-dive that arranges code-as-policy methods by their degree of self-improvement, from zero-shot program synthesis, through closed-loop self-repair and persistent skill memory, to the sparsely populated cell in which execution feedback, skill memory, and evolutionary search combine into one open-ended loop; only a few very recent systems (for example ASPIRE, ENPIRE, and RoboClaw) occupy that cell. We map the complementary "skills" pole, from unsupervised reinforcement-learning skill discovery to large-language-model skill libraries, and show that the word "skill" is used in at least five distinct senses, of which only the code sense self-improves without gradient updates. We then connect the taxonomy to the emerging skill economy: commercial robot-skill marketplaces now distribute one-tap skills across robots but ship only static playback, which surfaces open problems of adaptation, cross-embodiment portability, provenance, safety verification, composition, and standardisation. This is a deliberately focused survey. Rather than cataloguing the field exhaustively, it examines 77 representative systems across six technique families through one taxonomy and a set of contrast tables, and it supplies operational definitions of the self-improvement mechanisms together with a statement of what each family cannot do.

arXiv

Physics-Informed Neural Networks for Complex Eigenfrequency Identification and Mode Structure Reconstruction of the Ground-State ITG Branch

Dengdi Sun, Bingbing Zhang, Xiao Wang, Zikang Yan, Yuqiang Tao, Qingquan Yang, Guosheng Xu, Jin Tang

Physics-informed neural networks (PINNs) combine sparse observations with physical equations, providing an important approach for modeling complex plasma processes and inferring unknown physical quantities. The steep-gradient pedestal of high-confinement-mode tokamaks is closely linked to plasma confinement and edge transport. Analyzing ion-temperature-gradient (ITG) drift waves in this region requires jointly identifying complex eigenfrequencies and reconstructing two-dimensional complex-valued mode fields. Localized high-frequency oscillations, strong real-imaginary coupling, and nonlinear coupling between the mode field and eigenfrequency challenge PINN representation and joint optimization. To address these challenges, we propose a physics-informed neural framework combining Fourier feature encoding, complex-valued feature propagation, and three-stage training. Under sparse observations and physical constraints, it jointly solves for the complex eigenfrequency and mode field of a representative ground-state ITG branch. Experiments show that the framework accurately recovers the target complex eigenfrequency and two-dimensional complex-valued mode field and outperforms representative PINN baselines. It also provides a basis for analyzing higher-order and multiple-branch drift-wave modes.

arXiv

Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models

Junxiang You, Junkai Chen, Yuhao He, Ruiqi Liu, Zhetao Guo, Shu Wu

Machine unlearning offers a promising approach to remove unsafe content from Multimodal Large Language Models (MLLMs), yet ensuring the precision of unlearning remains a persistent challenge. One reason is that current MLLM unlearning evaluation paradigms suffer from a critical blind spot: they assess model utility through benchmarks whose representations are distant from the forget set, failing to capture knowledge holes---severe degradation on benign adjacent inputs. To probe knowledge holes in unlearned MLLMs, we construct a benchmark that captures unintended degradation on benign inputs sharing generic patterns with the forget set, and confirm through controlled experiments that they are a systematic consequence of commonly used approaches. Furthermore, to bridge this gap, we propose Selective Protection with Anchored Regularization, which protects generic patterns via anchored activation filtering while reinforcing them through entity-abstracted enhancement. Our experiments on SafeEraser demonstrate that SPAR recovers over 98% of vanilla response quality compared to below 50% for standard baselines---while achieving 0.00% attack success rate and competitive model utility. These results underscore the necessity of more fine-grained evaluation for trustworthy MLLM unlearning.

arXiv

FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling

Xianglong Yan, Hong Liu, ChengZhu Bao, Tianao Zhang, Guanghua Yu, Jianchen Zhu, Yulun Zhang

Large language models (LLMs) achieve remarkable performance but are expensive to deploy due to their enormous size. FP4 quantization, with formats such as MXFP4 and NVFP4, offers an appealing solution with native hardware support on modern accelerators. However, maintaining accuracy under FP4 precision remains difficult. A key bottleneck lies in scale optimization: existing methods tightly couple the quantization and dequantization scales, forcing both to conform to the discrete low-precision format required by hardware, such as E8M0 in MXFP4. Yet the quantization scale is never stored and need not obey this constraint, suggesting a significant untapped optimization space. In this work, we propose FOCUS, a post-training quantization framework with end-to-end scale learning for FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling. Coupled-Relaxation Scaling (CRS) relaxes the tight coupling between quantization and dequantization scales with a learnable full-precision coefficient, enabling more effective optimization without breaking hardware compliance. Dual-Granularity Scaling (DGS) further refines the quantization scale at a finer sub-block granularity, allowing more precise adaptation to local weight distributions. Experiments across multiple LLM families and benchmarks show that FOCUS achieves state-of-the-art FP4 accuracy under both MXFP4 and NVFP4 formats, while introducing no additional inference overhead. Code and quantized models will be released at https://github.com/tencent/AngelSlim.

arXiv

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Chunji Lv, Yangguang Wei, Junlin Liu, Yang Gao, Ming Liu, Xinming Wang, Jinyang Wu, Guoren Wang, Changsheng Li

Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-turn trajectory may receive only a single outcome-level signal. On-policy self-distillation (OPSD) provides dense token-level supervision from a privileged teacher, but the teacher may not be reliable at every position. Existing methods commonly rely on isolated token-level discrepancies, which can be sensitive to noise, or assign a shared step-level weight that may overlook positional variation. We propose Persistent Consistency Self-Distillation (PCSD), which derives token-level distillation weights from the local persistence of teacher-favoring signals. PCSD combines adaptive windows with exponentially decayed aggregation to capture persistent relative teacher support, applies trend-aware modulation to attenuate locally declining support, and produces continuous weights through sigmoid gating. The resulting objective is jointly optimized with GRPO, combining dense teacher guidance with sparse environmental feedback. Without inference-time skills, PCSD achieves the best ALFWorld Overall results among all baselines on both backbones, exceeding GRPO by 15.6 and 13.3 points and SDAR by 6.2 and 5.5 points, while remaining competitive on WebShop and gaining 15.8 points over GRPO on unseen ALFWorld split.

arXiv

Rewriting or Reweighting? A Geometric Account in Language Models

Juntong Wang, Shengkun Yang, Xiyuan Wang, Muhan Zhang

Post-training can substantially alter language-model behavior, yet aggregate behavior rates do not reveal whether training removes an existing mechanism, creates a new one, or changes how an inherited mechanism is used. We study this question through two mechanistically distinct failures, repetition as a decoding-attractor pathology and sycophancy as a preference-related alignment failure. We introduce behavioral manifold analysis, which isolates behavior-specific geometry by selecting sparse behavior-associated coordinates and lifting them into low-dimensional local charts. We construct these charts in two complementary spaces. ACT captures runtime activation states, while NOC quantifies how strongly the model routes functional information flow through the shared behavior-associated subspace. Across multiple model families, the resulting charts are highly compressed and partially alignable across architectures. Contribution-space charts expose a more architecture-robust shared core, whereas activation-space charts retain stronger family-specific structure. Tracking these charts through controlled post-training reveals a consistent asymmetry. Supervised fine-tuning substantially alters the inherited behavioral geometry, whereas reward optimization changes behavior while largely preserving the underlying chart. This geometric perspective provides a unified framework for understanding the mechanistic distinction between the two objectives. SFT tends to rewrite behavioral geometry, whereas reward optimization primarily reweights it. Code is available at https://github.com/ronglingze/Manifold-Analysis

arXiv

Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

Perry Dong, Ron Polonsky, Dorsa Sadigh, Chelsea Finn

Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function. In this paper, we systematically study whether pretraining the Q-function actually helps when fine-tuning on top of a pretrained base policy. We find, surprisingly, that naive Q-function pretraining often provides little benefit over random initialization. We show this stems from a fundamental mismatch: the Q-function learned during pretraining targets the pretrained policy's Q-function, not the Q-function that online fine-tuning converges to, and this gap persists even after offline value maximization. Motivated by this finding, we propose Initialization via Policy Ensemble (IPE), a simple method that trains multiple diverse policies and uses their pooled rollouts to bootstrap the Q-function learning in online RL. Across a suite of challenging continuous control benchmarks, IPE yields an average 1.26x improvement in fine-tuning performance over naive Q-function pre-training.

arXiv

SearchMaster: Grounded and Regulated Self-Play for Search Agents

Wentao Tan, Qiong Cao, Jiaqi Wang, Nan Duan

Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search tools effectively. Existing pipelines often depend on human-written tasks, expert demonstrations, or stronger teacher models. We present SearchMaster, a self-play framework that trains a single LLM from search tasks it generates, solves, and verifies in a local search environment. The key challenge is that self-generated tasks and rollouts can yield misleading signals: pseudo multi-hop questions, success-rate difficulty estimates that ignore search depth, and rollouts with excessive opening but little targeted evidence acquisition. SearchMaster addresses these failure modes with three controls. An Evidence-Chain Generator (ECG) grounds task generation in explicit cross-document evidence chains to reduce pseudo multi-hop questions. A Search-Depth Reward (SDR) scores task difficulty by the search depth of successful rollouts rather than success rate alone, keeping retained tasks search-intensive. An Over-Opening Penalty (OOP) regulates tool use by discouraging excessive document opening, avoiding long but shallow browsing. Verified Proposer and Solver rollouts are then jointly optimized with GRPO. Across six deep-search benchmarks, SearchMaster improves a Qwen3.5-9B backbone from 38.19% to 51.52% average accuracy, with a 30.1-point gain on BrowseComp-Plus. These results show that grounded and regulated self-play can provide effective search-agent training data without human-labeled QA pairs or expert demonstrations. The code is available at https://github.com/WentaoTan/SearchMaster.

arXiv

CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits

Wei Wang, Shuanghe Liu, Zhu Zhuo, Jiaqi Zhong, Xiaozhao Zhao, Xiaojie Zuo, Jie Su

LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures. This is especially hazardous in safety-critical embodied settings such as automotive cockpits, where lexically correct utterances may trigger dangerous physical operations. Existing attribution methods rely on text traces alone, missing dependency structure, multi-channel evidence, and safety-aware evaluation. We introduce CockpitHAT, a hierarchical attribution framework that replaces positional windows with dependency-distance thresholds from interaction DAGs, integrates multi-channel evidence via an embodied adapter, and applies a safety-uplift to high-risk failures during confidence-weighted analyst consensus. We further release CockpitBench, a benchmark of 212 annotated failure traces spanning dialogue, vehicle-state, environmental, and memory channels, each labeled with ISO 26262 ASIL severity via three-expert consensus. On the public Who&When benchmark, CockpitHAT achieves agent-level / step-exact accuracies of 77.9% / 37.8% on the Hand-Crafted split and 86.5% / 46.0% on the Algorithm-Generated split, surpassing the text-only SOTA ECHO by up to 17.6 / 16.7 points. On CockpitBench, it attains 78.3% agent-level and 38.2% step-exact accuracy. These results establish dependency-aware, multi-channel, risk-calibrated attribution as an effective paradigm for reliable failure diagnosis in real-world embodied LLM multi-agent systems.

arXiv

CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning

Junru Song, Wenhao Zhang, Yang Yang, Xuekai Qiu, Feifei Wang, Weien Zhou, Tingsong Jiang, Ying Wen, Yang Li, Wen Yao

Target-oriented vision-and-language navigation (VLN) on aerial platforms is attracting growing attention for missions such as disaster rescue, infrastructure inspection, and security patrol. In this task, an unmanned aerial vehicle (UAV) needs to locate targets given only a concise description of their appearance and surroundings. This requires global exploration and grounding as well as collision-free close-range approach, two interleaved processes difficult to reconcile within a single agent. Most existing methods transfer the ground VLN paradigm to a low-altitude UAV and compensate for its inefficient exploration with external assistance. A recent attempt deploys two UAVs at complementary altitudes yet still relies on privileged information and trains its two agents independently, precluding any mutual adaptation essential for cooperation. Here we propose CoNav-UAV, which explicitly models the task as a Stackelberg game between a high-altitude leader and a low-altitude follower, with the system operating on onboard visual and linguistic inputs alone. To solve this game, we introduce Iterative Stackelberg Learning. The leader's high-level vision-language reasoning is refined via memory-based in-context learning, while the follower's precise motion control is updated via DAgger-style expert distillation. The alternation drives both agents toward a Stackelberg equilibrium. CoNav-UAV consistently outperforms single- and dual-agent baselines across three high-fidelity urban scenes from the AerialVLN benchmark. Success rate improves by up to 30.8 points on the learning scene, and 9.0 points under cross-scene transfer while using about 3x less adaptation data. Further analyses validate the complementary gains of the leader and follower updates and reveal robust gains yet distinct learning dynamics across VLM backbones.

arXiv

Radar Detection in the CBRS Band: Techniques, Challenges, and Future Directions

Madan Baduwal, Priyanka Paudel

The 3.5 GHz Citizens Broadband Radio Service (CBRS) is a shared wireless band that allows both government systems and commercial networks (such as private LTE/5G) to use the same spectrum. To prevent interference with critical government systems, especially naval radars, CBRS uses a monitoring system called the Environmental Sensing Capability (ESC). ESC acts like a network of sensors that continuously listens for radar signals and alerts the system when they are detected, so commercial users can temporarily stop or adjust their transmissions. This paper reviews how radar signals are detected within the CBRS band. We first explain the regulatory framework and describe the types of radar signals that need to be identified. We then examine traditional detection methods, such as energy-based and pattern-matching techniques, and compare them with newer approaches based on machine learning and deep learning, which can automatically learn to recognize radar signals from data. We also review publicly available datasets and testing platforms used to evaluate these detection methods, along with key performance requirements such as high detection accuracy (e.g., 99% detection probability (radar overlap recall)) and low delay (e.g., within 60 seconds). Finally, we highlight current challenges, including false alarms, interference from modern wireless systems, and the need for real-time operation. Overall, this survey shows that while traditional methods are simple and reliable in controlled settings, modern learning-based approaches offer better performance in complex environments. The future of CBRS radar detection will likely combine both approaches to achieve accurate, fast, and robust performance in real-world deployments.

arXiv

Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems

David Bauer, Cancan Zhang, Wenshun Liu, Xiaoyi Zhang, Weijia Liu, Wanli Ma, Yue Weng, Wei Li, Rui Li, Jing Qian, Huayu Li, Xiaoyi Liu, Linhong Zhu, Jerry Fu

Recommendation systems have undergone significant transformations in the past years. The transition from traditional feature interaction modules to generative next-action prediction has pushed the boundaries of personalized content. Developments have largely evolved along two separate tracks. Sequence modeling approaches on the one hand and feature interaction methods on the other. In this paper, we introduce Bumblebee, a recommendation architecture that addresses the lack of interaction between the two directions through an interleaved, stackable block design. Each block implements a micro-pipeline of layers combining sequence personalization, attention-based encoding, and feature crossing into a self-contained unit. Every block produces a joint representation of both feature modalities which is consumed by the next block in the sequence. This mechanism encourages early and repeated mixture of modalities and enriches downstream features with additional contextual information. Residual connections between blocks create cross-modal information pathways and yield additional predictive performance without adding additional parameters. Blocks can be specialized by selectively dropping components, enabling flexible trade-offs between quality and throughput. We evaluate our approach on large-scale industrial data and show consistent improvements over comparable baseline models across several classification and regression tasks. Furthermore, we conduct ablation studies to confirm that the interleaved composition itself is the primary driver of these improvements. Our results suggest that interleaving heterogeneous functional units, rather than composing deep stacks, is a promising paradigm for future-generation recommendation architectures.

arXiv

WCM: World-Cognition Model for Generalizable Human-Robot Interaction

Yuzhen Chen, KC Zhou

Language agents can now interact fluently with users in software, but robots still struggle to bring comparable interaction to physical tasks. Current robot-control paradigms, including vision-language-action policies and world-model-based planners, are mainly optimized for instruction execution, leaving users with little visibility into why an action is chosen and few mechanisms to redirect, correct, or teach the robot through interaction. To solve this problem, we present the World-Cognition Model (WCM), a human-centered embodied agent built on the SLAK architecture (Sensing, Logic, Action, and Knowledge) and an asynchronous runtime. SLAK separates perception, reasoning, control, and memory, while the runtime allows reasoning, dialogue, and execution to proceed concurrently. WCM further introduces a human-in-the-loop teaching mode that enables users to interactively teach the robot difficult or long-horizon tasks. Teaching episodes and autonomous task rollouts are refined into chain-of-thought supervision to continually improve the model. WCM achieves a 73.8% average success rate across nine real-world human-robot interaction tasks, including tasks held out from CoT fine-tuning and a long-horizon task learned through teaching.

arXiv

FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows

Xuhui Wang, Ruoqi Shu, Chen Dan, Tianhua Xu, Mengxi Luo, Yanming Mai, Bo Wan

LLM agents increasingly run policy-bound enterprise workflows such as document auditing, where they must apply rules consistently, ground every value, and stay auditable. Improving these agents is hard: operational feedback is sparse and unlabeled, edits to one rule can regress unrelated cases, and accuracy must improve without inflating inference cost or losing auditability. We present FRAMES, a closed-loop framework that cold-starts deployable skills from existing assets and then evolves them through consensus-based mutation, Pareto selection over accuracy and cost, and an anti-regression guarantee, all while preserving auditability. Deployed on our internal production system, FRAMES attains the best accuracy-cost trade-off among baselines, with the same gains reproduced on tau-bench.

arXiv

Leveraging AI for fine-grained food safety risk forecasting in sparse data conditions

Dongqi Wang, Weiwei Chen, Han Zhou, Weihua Zhou

Ensuring food safety represents a critical public health challenge, particularly when inspection resources are limited and regional sampling data are sparse. This study proposes a Transformer-based framework capable of forecasting fine-grained, city-level food safety risks by unifying over 11 million inspection records with supplemental demographic, economic, and environmental indicators extracted from the Statistical Yearbook. A three-stage pretraining design leverages partial supervision from the Wilson interval (capturing both safety and risk rankings), together with semi-supervised label refinement, to effectively utilize historical records even when local sample sizes are insufficient. Experimental evaluations on data from 2022 show that the proposed approach outperforms baselines significantly. A subsequent field experiment in collaboration with the Zhejiang Provincial Administration for Market Regulation further demonstrates improved detection rates and more efficient allocation of inspection resources compared to a manually developed plan. Observations of regulatory decision-making reveal a threshold-based heuristic employed by inspectors, hinting that additional training or decision-support interfaces could further enhance the impact of AI-generated risk scores. Overall, these findings underscore that a rigorous integration of large-scale public inspection data, Wilson interval-based confidence modeling, and advanced deep learning can facilitate earlier and more granular identification of food safety threats. By reducing reliance on reactive measures alone, the proposed framework has the potential to advance proactive, data-driven oversight of the global food supply.

arXiv

EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming

Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne, Paulo Shakarian, Dana Warmsley, Nigel Stepp, Evelyn Kim

Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge, limiting their reliability in safety-critical settings such as medical devices. Prior work either treats that output as a prediction to be scored or constrains it to walks within a single knowledge graph; neither checks whether reasoning over a binary is consistent with an independent body of domain knowledge. We present EntailLLM, which validates each LLM-proposed analyst path by entailment: the path is a traversal of the binary's function call graph, the domain knowledge is represented in a separate graph, and verification aligns the two under temporal annotated logic. Across three CWE classes, four LLMs, three prompting strategies, and seven binaries varying in size from 405 to 12,696 function call-graph nodes, domain knowledge raises pooled entailment from 78% to 98%, with entailment decreasing in only 3% of the experiments. EntailLLM is deployed end-to-end on real medical-device binaries, reaching 98% pooled entailment without per-device tuning. Our system inherits the formal guarantees of generalized annotated logic, providing logical verification of LLM output that is both explainable and grounded in well-defined semantics.

arXiv

RL-Lock: Reinforcement Learning for Generating Interlocking Assemblies

Xuyang Ma, Chaewoon Kim, Haonan Zhang, Rulin Chen, Ziqi Wang, Peng Song

An interlocking assembly is an assembly in which component parts are connected purely through their geometric arrangement, without relying on external connectors such as glue and nails. Such assemblies have been widely used in a variety of real-world applications due to their structural stability. The problem of generating interlocking assemblies is generally formulated as a shape decomposition problem, where a target 3D object represented as a voxel grid is partitioned into a prescribed number of interlocking pieces. We observe that generating interlocking assemblies is inherently a sequential decision-making problem, where an agent repeatedly decides which piece each voxel should be assigned to. Inspired by the observation, we propose the first reinforcement learning framework RL-Lock for generating interlocking assemblies, without relying on handcrafted search heuristics as existing works did. RL-Lock combines structured action chunking with MCTS-guided policy-value learning to efficiently navigate the large combinatorial search space for interlocking assembly generation. We demonstrate through experiments that RL-Lock allows effective generation of interlocking assemblies, especially for challenging cases in which existing approaches take too long or even fail to find a valid solution.

arXiv

CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents

Bowen Ye, Yongchao Xu, Zhijian Li, Xiang Yin, Junkai Ma, Wenzhao Li

As memories accumulate across tasks and sessions, the performance of long-term LLM agents depends jointly on query-specific retrieval and continual memory refinement. However, existing methods typically optimize either memory access, through iterative query refinement or adaptive retrieval policies, or memory evolution such as structural update. This separation overlooks a fundamental feedback loop: retrieval determines which memories receive usage signals, while updated memory bank reshape future retrieval. We propose \textbf{CoEvo-Mem}, a closed-loop framework for co-evolving the retrieval policy and memory bank. For each query, a frozen LLM generates route-specific query rewrites and a routing prior, which a lightweight residual router corrects online. The retrieved context serves as the coupling interface between the two learning processes: task outcomes assign credit to routing decisions, while trajectory-conditioned feedback updates memory values and graph relations. These updates alter how memories are ranked and selected for subsequent queries, thereby closing the feedback loop. To mitigate coupling induced non-stationarity, CoEvo-Mem alternates between updating the router with the memory bank fixed and evolving the memory bank with the retrieval policy fixed. Across seven diverse benchmarks, \textbf{CoEvo-Mem} achieves state-of-the-art performance, demonstrating the importance of retrieval-memory coevolution.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.