Autonomous
-
OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression
2026-10-08 15:23:02Sixu Chen, Mingrui Yang, Qiang Guan, Xiaojuan LiAbstract
Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of multimodal data and multidomain expertise. Moreover, isolated risk estimates provide limited insight underlying a prediction. To automate the progression assessment workflow and reduce manual effort while providing interpretable findings and supporting evidence, we present OA-MAP, an autonomous multi-agent framework for evidence-grounded assessment of structural and pain progression in KOA. The system incorporates modality-specific agents including MRI, X-ray, and clinical agents, together with a coordinator agent. This framework can autonomously recruit specialist agents, select tools for prediction and analysis, and retrieve literature as external evidence based on user request and available patient information. An uncertainty-informed human-in-the-loop mechanism enables clinicians to review and correct intermediate findings, triggering recomputation of affected results. We evaluate the prediction models using 600 participants from the FNIH Osteoarthritis Biomarkers Consortium cohort. On the test set of 100 participants, the fusion models achieve AUROCs of 0.80 for structural progression and 0.68 for pain progression. A case study illustrates how OA-MAP combines risk estimates with intermediate findings, cross-modal conflicts, literature support, and uncertainty indicators to support interactive review.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12134
PDF
-
Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents
2026-10-08 15:16:56Xiangyi Zeng, Baihang Liu, Xutong Wang, Ze Jin, Yunpeng Li, Qixu LiuAbstract
The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws inspiration from two characteristics of human memory: cognitive processes selectively maintain information relevant to current goals, while long-term memories form gradually through repeated consolidation. Accordingly, Hippocam structures an agent's ongoing work as nested intents. The active context remains centered on the current intent, while completed intents are consolidated into the task-relevant outcomes and state needed for subsequent work, rather than carrying forward their full working details. Concurrently, a recursive prefix consolidation mechanism repeatedly consolidates earlier history, causing long-unused experiences to become increasingly abstract. Original interactions are preserved, allowing the agent to progressively recover finer-grained details through the hierarchy and stop once sufficient information is available. Crucially, when past experiences are recalled and reintegrated into active work, they undergo subsequent consolidation alongside new experiences, thereby being reinforced, supplemented, and updated. Through this memory dynamic of use and disuse, Hippocam connects working context, long-term memory, knowledge accumulation, and skill learning within a single continuously evolving experiential process. This enables agents to learn and evolve capabilities through their own experiences without parameter updates.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12124
PDF
-
Agentic-TTT: Training test-time policy for test-time training
Abstract
Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment experience into parameter updates, TTT provides a direct mechanism for model-level self-improvement. Yet TTT is not universally beneficial: each TTT algorithm works in different settings, and applying an ill-suited method could waste test-time compute or even damage model performance. Therefore, such parameter-level self-improvement requires agency: the model must decide when TTT is warranted, which algorithm to invoke, and whether an existing skill can be reused. To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions. Agentic-TTT turns TTT procedures into callable tools, treats accumulated skills as an evolving deployment environment, and trains its policy using the observed utility gains from its decisions. On our benchmark, Agentic-TTT nearly doubles the utility over the backbone model, learns to trade off utility against compute, and generalizes to domains unseen during training. Together, these results point toward autonomous self-improvement: models that can decide how to learn from their own deployment experience.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12002
PDF
-
STAG: A Sparse Traversability-Aware Graph Representation from Grid-Based Costmaps for Robotic Navigation
2026-10-08 13:33:38Gabriel Manuel Garcia, St\'ephanie Aravecchia, Miguel Angel Olivares-MendezAbstract
Autonomous rovers navigating large unstructured environments need efficient global planning that accounts for terrain traversability. However, searching dense grid-based costmaps becomes computationally expensive as the mapped area grows. We introduce STAG, a Sparse Traversability-Aware Graph that converts costmaps into compact graphs. STAG combines a medial-axis topological backbone, representative nodes for homogeneous traversability regions, and transition nodes near strong traversability gradients. Edges encode geometry and traversability to account for path length and terrain difficulty. We compare A* on STAG and dense grids using synthetic cave maps, mine maps and the DARPA CERBERUS dataset. Across five benchmark categories comprising 203 map instances and 101,200 queries, STAG reduces median planning time by 3.4x to 9.9x and peak query memory by 2.1x to 15.4x, with median relative path-length differences of -2.9% and +7.6%. STAG offers a compact representation for global planning, trading dense-grid traversability optimality for faster, less memory-intensive search.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11943
PDF
-
Digital Twin for Pre-Deployment Validation of AI-Driven Safety-Critical Industrial Edge Control Loops
2026-10-08 13:28:53Sara Cavallero, Federico Tonini, Tony Chahoud, Giampaolo Cuozzo, Davide Borsatti, Walter Cerroni, Maurizio Fodrini, Riccardo MariniAbstract
Industrial environments are increasingly characterized by the tight interaction among physical processes, communication infrastructures, and intelligent applications. In this context, Digital Twins (DTs) have emerged as a key technology for system analysis and optimization. However, existing DT solutions typically focus either on industrial processes or communication networks, while lacking an integrated and application-aware perspective. To fill this gap, this paper proposes a modular DT framework for industrial environments that jointly models physical processes, wireless communications, and application logic within a unified architecture. The feasibility of the proposed framework is experimentally validated through a real-world Proof-of-Concept (PoC) implemented in the BI-REX pilot line, involving a 5G-connected Autonomous Mobile Robot (AMR) transporting hazardous liquids and remotely controlled by an AI-driven application. The proposed DT is used to reproduce the behaviour of the real deployment and to investigate the impact of different placements of the AI application, including on-premise, edge, and remote cloud execution scenarios. Experimental results demonstrate a close agreement between DT predictions and PoC measurements in terms of both network-level metrics, such as Reference Signal Received Power (RSRP) and latency, and end- to-end application metrics, including application-level Round- Trip-Time (RTT). Moreover, the analysis shows how inaccuracies of network modeling can critically affect the feasibility of latency-sensitive industrial control loops, highlighting the potential of integrated DTs as tools for the pre-deployment design and validation of next-generation industrial systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11934
PDF
-
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
2026-10-08 13:05:33Irene Weber (University of Applied Sciences Kempten, Germany)Abstract
Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent. Whether these labels denote genuine architectural forms or serve as branding has not been assessed systematically. In the sources surveyed, labels do carry architectural content, most clearly in vendor usage: copilot denotes a router-worker architecture operating a host application under step-by-step user confirmation, while the more recent shift to the label agent coincides with AI-planned multi-step execution of which the user sees only the outcome. The coding agents of four major providers share one architecture, a reason-and-act loop delegating to subagents. This survey describes seven recurring forms---LLM chats, custom agents, retrieval-augmented generation (RAG), AI-enhanced workflows, copilots, coding agents, and, in part, agentic RAG---in a common vocabulary of agents and tools. Each is characterized along four structural dimensions (agentic RAG only partially): the architectural pattern, the control of execution and the point of user intervention, the number of agent calls per task, and tool use. An illustrative corpus of 22 systems from research publications and vendor documentation grounds the descriptions and shows where they reach their limit.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11899
PDF
-
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
2026-10-08 12:06:54Haoyu Zhao, Zhengxu Yu, Zhiyuan He, Meng Fang, Rasul Tutunov, Haitham Bou-Ammar, Weilin Luo, Jun WangAbstract
Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions but predict different outcomes in unseen states. We introduce Memento 3, building on the Memento series to enable frozen LLM agents to continually learn explicit world models through external memory. The agent maintains a natural-language rulebook as persistent semantic memory, recording revisable hypotheses about environment dynamics while leaving unknown aspects underspecified. It compiles this rulebook into executable code for prediction and planning. Through a continual loop of observation, reflection, rule revision, compilation, and verification, the agent uses prediction errors to refine both the rulebook and its code. Updated code is accepted only when the LLM judges it faithful to the rulebook and cell-exact replay reproduces the observed transitions. We investigate this process as a model-based route to recursive self-improvement (RSI): the agent autonomously explores the environment, revises its world model, and uses verified updates to guide subsequent interaction and learning, while the underlying LLM remains fixed. A population extension maintains multiple world models in parallel, sharing interaction evidence and using their predictions to guide exploration. On ARC-AGI-3, the single-model agent clears every level of all 25 public games, achieves a mean Relative Human Action Efficiency (RHAE) of 100.0, and uses 44% of the human action count. In an Atari Pong case study, a learned feedback controller wins 21:0 in each of three evaluated episodes with different openings, without further LLM calls.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11794
PDF
-
UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural Robotics
2026-10-08 11:47:33Dhanushka Balasingham, Shamod Ginigaddarage, Hanojhan Rajahrajasingh, Nuwan Kodagoda, Rajitha de SilvaAbstract
Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and inference time. This paper addresses crop-row detection and navigation-line extraction using UltraLight Luma, a compact encoder-decoder segmentation network with a progressive learning strategy and only 13.1k trainable parameters. The predicted crop-row masks are processed using a post-processing algorithm to estimate row alignment for downstream visual servoing. UltraLight Luma improves parameter efficiency over U-Net, YOLOv8, and YOLOv26 while maintaining reliable crop-row detection performance. The model required only 25.23 mJ per inference, demonstrating its suitability for resource-constrained agricultural robots.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11764
PDF
-
Autonomous thermodynamic cycles via robotic mobility and sensing
2026-10-08 10:39:27Sofia Kuperman, Ezra Ben-Abu, Yaron Veksler, Anna Zigelman, Sefi Givli, Amir D. GatAbstract
Thermodynamic cycles are the foundation of energy conversion across natural and engineered systems, transforming heat into useful work. However, these cycles traditionally operate between fixed thermal reservoirs, restricting them to specific locations and temperature differences. Here, we introduce autonomous thermodynamic cycles enabled by robotic mobility and sensing, allowing robots to perform thermodynamic cycles by accessing spatially varying temperature fields. We experimentally realize this concept using multistable gas-filled capsules that circulate within the system across a thermal gradient. Our model reveals that rapid transitions in the capsules' energy states allow the system to operate as a mobile heat engine that harvests and stores energy. By linking the capsule-scale internal energy dynamics to the robot's large-scale navigation strategy, we optimize locomotion paths that balance motion cost and energy harvesting. These findings demonstrate that thermodynamic cycles can emerge when autonomous systems navigate their environments, offering an artificial analog of organisms that forage for energy across spatial resources.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11667
PDF
-
Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition
2026-10-08 10:36:41Yichun Ye, He Zhang, Ye Tian, Jian SunAbstract
Autonomous driving capabilities depend strongly on the distribution of scenarios encountered during training. Existing methods commonly construct or dynamically adapt training scenario distributions using surrogate criteria such as realism, difficulty, or risk. However, these predefined surrogates may misrepresent training value, leading to inefficient use of training resources. To address this limitation, we propose a Lamarckian evolutionary framework that replaces surrogate-based guidance with competition among candidate distributions. We formulate training strategy discovery as a multi-stage bilevel optimization problem and use Lamarckian evolution algorithm to approximate its solution. At the outer level, Darwinian crossover, mutation, and selection explore the scenario distribution space; at the inner level, policy learning acquires new capabilities, and Lamarckian inheritance transfers them to subsequent stages, allowing scenario distributions and policy capabilities to co-evolve. The resulting evolutionary trajectories reveal recurring stage-wise regularities among high-value distributions, characterized by capability accumulation through stage-wise challenge rotation. We further distill these regularities into a lightweight, reusable Lamarckian Training Strategy. Experiments show that, compared with the baseline, the complete framework reduces performance loss by up to 25.07%, while the lightweight strategy still achieves a 19.13% reduction. These results demonstrate that evolutionary competition can both discover effective training strategies and reveal reusable stage-wise patterns in how the value of training distributions changes with policy capability. Code is available on GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11662
PDF
-
SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
2026-10-08 09:33:19Chengjun Zhang, Yuhao Zhang, Jie Yang, Mohamad SawanAbstract
End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (ANN) planners meet the accuracy requirement at the cost of heavy dense computation, while spiking neural networks (SNNs)---though promising orders-of-magnitude energy savings through sparse, event-driven arithmetic---still lag far behind in planning accuracy. We present \textbf{SDPAD}, a fully spike-driven end-to-end planning pipeline that closes this gap. SDPAD converts a pre-trained ANN perception stack into integer-spike form via quantized ANN2SNN conversion, lifts multi-view images into the bird's-eye-view (BEV) space with a spike-driven-max (SDM) depth distribution (Spike-3D-Lift), and plans through the Spike-QFormer, a spiking query transformer in which ego, agent, and map queries distilled from the BEV scene are fused by learnable waypoint queries via cross-attention, followed by deformable spike-cross-attention refinement. Every operation is gated by integer spikes and inference is a single feed-forward pass without temporal simulation loops. On the nuScenes open-loop benchmark, SDPAD achieves an average $L_2$ error of 0.40\,m and a collision rate of 0.12\%, on par with strong ANN planners while consuming 69.9\,mJ---less than 2\% of recent ANN baselines. In closed-loop evaluation on the NAVSIM navtest split, SDPAD reaches 86.3 PDMS, surpassing the previous SNN planner SAD by 4.3 points and matching mainstream ANN planners at a fraction of their energy. To our knowledge, SDPAD is the first fully spike-driven planner evaluated in end-to-end autonomous driving, demonstrating that SNNs can rival dense ANNs in complex driving tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11583
PDF
-
CoCam4D: Geometry-Aware Cooperative 4D Perception for Camera-Only Autonomous Driving
2026-10-08 09:31:28Soham Pahari, Sudip Das, Arindam Das, Ujjwal BhattacharyaAbstract
Autonomous vehicles often suffer from limited perception due to occlusions, blind spots, limited sensor range, and the complex nature of surrounding environments. Multi-agent collaborative perception (CP) addresses these challenges by allowing vehicles to share sensory information and reconstruct the scene cooperatively. However, camera-only perception remains fundamentally limited by the uncertainty of distance-dependent monocular depth estimation. We propose CoCam4D, a Bayesian framework for collaborative perception that explicitly models geometric uncertainty. It uses a VGGT-based feedforward network to generate 3D Gaussian scene representations with associated uncertainty estimates, enabling multiple vehicles or agents to efficiently combine their observations. By sharing compact Gaussian primitives, reliable observations from one agent can reduce the depth uncertainty of another without requiring LiDAR sensors. To support real-world deployment, we introduce Dynamic Object Primitives (DOPs), a compact 35-byte representation designed for efficient C-V2X communication. Extensive experiments show that our proposed method consistently outperforms recent vision-only methods, achieving improvements of 11.48% on OPV2V+ and 10.62% on DAIR-V2X-C, demonstrating the potential of geometrically grounded collaborative perception for LiDAR-free autonomous driving.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11577
PDF
-
Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating
2026-10-08 09:12:13Lechen Li (State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau 519000, China, College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, China), Rongye Shi (School of Artificial Intelligence, Beihang University, Beijing 100191, China), Wanhuan Zhou (State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau 519000, China)Abstract
Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated parameters. Existing hybrid evolutionary algorithms typically rely on static architectures or fixed switching rules, resulting in disjointed search phases. To address this, this study proposes a Deep Reinforcement Learning-governed dynamic DE-CMAES Orchestration (DRL-DCO) algorithm, in which a Deep Deterministic Policy Gradient (DDPG)-based actor-critic agent continuously governs the evolutionary process as a single, unified system rather than a mechanical concatenation of algorithms. Guided by a progression-aware state representation and a diversity-informed reward, the agent fluidly reallocates computational resources between the differencevector-based exploration of Differential Evolution (DE) and the covariance-guided exploitation of CMA-ES, while jointly regulating population size, elite preservation, and a restart mechanism to escape local optima. This allows DRL-DCO to autonomously transition between exploration-dominant, exploitation-dominant, and mixed-strategy regimes across generations. Beyond the training phase, the trained actor can operate in a supervision-free inference mode, where the internalized policy autonomously orchestrates DE and CMA-ES control from observed search states through forward inference alone, without critic evaluation or weight updates, enabling faster deployment while retaining full effectiveness. Validated on high-dimensional single-objective optimization benchmarks and the IASC-ASCE structural health monitoring benchmark, DRL-DCO achieves superior convergence accuracy and robustness compared to state-of-the-art adaptive and hybrid evolutionary algorithms, as well as single-operator DRL-governed baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11546
PDF
-
AgentTime: Can Agents Estimate and Control Their Own Runtime?
2026-10-08 09:06:36Michael Ofengenden, Maksym AndriushchenkoAbstract
An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward. It comprises 222 tasks from 18 sources spanning coding, computer use, agentic work, and automated research. Duration-following experiments append a single instruction specifying how long to work, with requests ranging from about a minute to multiple days. Accuracy on these instructions varies substantially: Fable 5.1 in Claude Code deviates from requested runtimes by a typical factor of 2.9$\times$, compared with only 1.2$\times$ for GPT-6 Astra in Codex. However, matching the requested runtime does not, by itself, establish continued work on the task. Among 158 reviewed Astra runs with classifiable transcripts, 14 explicitly slept after appearing to finish. In forecasting experiments, predictions tend to overestimate natural runtimes. In retrospective experiments, removing temporal information more than doubles deviation for Sol and Astra and nearly doubles it for Fable. An agent's ability to complete a task does not guarantee that it can control its own time or work for the whole requested duration. For agents to run reliably, safely, and autonomously over long horizons, we require the evaluation of both.
Abstract (translated)
URL
https://arxiv.org/abs/2610.09944
PDF
-
The Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute
Abstract
Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These models are accurate, but they cannot be deployed through standard inference runtimes. The reason is an operator mismatch between dense convolutions (which runtimes handle well), sparse 3D convolutions (which runtimes cannot represent), and geometric scatter operations (which runtimes have no vocabulary for). Today, every sparse convolution library is CUDA-only and PyTorch-coupled, locking BEV deployment to a single vendor's hardware and a single execution framework. We present BEVPIPE, a framework for deploying multimodal BEV perception pipelines using portable GPU compute APIs and integrating them with production inference runtimes. BEVPIPE partitions the model into runtime-managed dense subgraphs and three external operator extensions (voxelizer, sparse encoder, BEV projector), connected through a shared GPU memory space. BEVPIPE achieves a 19.5x end-to-end speedup over conventional deployments while retaining 98.5% of reference mAP. We also showcase that BEVPIPE is portable across different GPU backends.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11504
PDF
-
BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
2026-10-08 08:26:52Zhenjun Qiu, Jianing Huang, Dongang Liu, Baiyu Du, Yixun Niu, Hao Yang, Xinyu Huang, Chuan Hu, Shu LiuAbstract
Diffusion-based driving planners capture diverse behaviors but can generate unsafe trajectories under distribution shift. We propose BridgeGuard, a safety-constrained diffusion planning method that progressively strengthens a constraint term during denoising to drive intermediate trajectories toward a scene-dependent safety domain. Corrections operate in a low-dimensional curve space, promoting geometric coherence. A learned module, DistanceFieldNet, predicts a time-dependent distance field from bird's-eye-view features. Value and spatial-gradient supervision at queries sampled beyond expert trajectories teaches this field about both safe and unsafe regions. The learned field supplies the constraint term through safety injection while the pretrained perception backbone and planner remain frozen. We further establish sufficient conditions for terminal safety in an idealized continuous-time bridge. On Bench2Drive, BridgeGuard improves driving score/success rate from 87.99/74.99% to 90.88/76.36% for BridgeDrive and from 80.79/58.18% to 90.46/74.09% for $\text{DiffusionDrive}^{\text{geo}}$, demonstrating cross-model generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11483
PDF
-
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
2026-10-08 08:17:45Chiara Bonfanti, Cataldo BasileAbstract
We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable. The system performs controlled, read-only collection of public traces and preserves selected observations for later resolution. In a frozen September 2026 corpus, several collected traces became more informative as additional public evidence emerged. The strongest result concerns Census-labelled identifiers captured on 9 September. Public revision records later resolved these identifiers to specific Census requests from 16 - 17 June. Other results show weaker links between traces collected by GROB and evidence reconstructed or reported later. These links vary in strength, and only some can be tied to specific public records. The results show that sparse public traces can remain useful even before their significance is fully understood. Such evidence can support later reconstruction, but public traces alone do not establish organizational attribution. Execution identity presents a separate problem, as continuity of agent identity remains an active research question for autonomous language-model agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11467
PDF
-
Generative Adversarial Loops
2026-10-08 08:11:37Kislay Aditya Oj, Nidhi Jain, Sri Surya Varma Datla, Priyanka Jayaswal, Kumar Krishna Agrawal, Aditya DesaiAbstract
AI research progress can be viewed as the interaction between two processes: benchmark creation and method discovery. Historically, both were driven by human intelligence. However, recent advances in AI have accelerated automated method discovery, while automated benchmark creation has received comparatively less attention. To enable self-advancing systems, we propose Generative Adversarial Loop (GAL), a generator-discriminator framework alternating between two agentic searches: (1) a discriminator that generates adversarial data to expose weaknesses in current systems, and (2) a generator that discovers algorithms to overcome them. We apply this framework to approximation algorithms for efficient inference. Unlike existing auto research systems, which primarily focus on algorithm discovery, GAL introduces a discriminator agent that automates goalpost setting by continually searching for weaknesses in the current algorithm. We demonstrate adversarial data generation across four tasks: KV compression, sparse video generation, sparse attention, and context extension, where the discriminator identifies weaknesses in state of the art techniques. We further show that GAL enables autonomous improvement, with newly discovered algorithms improving not only on adversarially generated data, but also on established benchmarks. Specifically, GAL improves CompactorPress on KV compression with Qwen3-4B at 4x, raising performance on the discriminator dataset from 0.35 to 0.97, while also outperforming RULER-HARD (+0.77 pts). For context extension, GAL boosts Dual Chunk Attention from 0.20 to 0.90 on the discriminator dataset, while yielding gains on standard benchmarks(ScienceFiction (+6 pts) and PG19 32K (-0.33 PPL)). GAL thus provides a path toward autonomous goalpost setting and algorithmic improvement, where AI systems continually discover their own weaknesses and develop methods to overcome them.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11458
PDF
-
PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving
2026-10-08 07:13:10Jinchang Xu, Hongda Yu, Fengwei Dong, Wenhui Huang, Xi Wei, Yongzhi Liu, Sunan Zhang, Jirao Wang, Chen Lv, Bingbing Li, Guodong Yin, Weichao ZhuangAbstract
World models in end-to-end autonomous driving predict future scene evolution to provide foresight for trajectory planning. Existing methods mainly study how to predict the future and how to use it, but less often ask which future representation is actually most useful for planning. To this end, we propose PlanWAM, a Planning-Shaped World Action Model. The key idea is to let the planning task shape the future-state representation, so that it retains the information most useful for planning. A latent world model then predicts this planning-shaped future latent representation from historical observations and uses it for planning, enabling foresighted planning. Specifically, we first use a Temporal Register Pyramid to compress multi-frame historical information in a recency-aware manner, learning a compact history representation oriented toward future reasoning and planning. We then introduce a privileged future posterior branch that observes ground-truth future frames, and shape its future latent representation with trajectory-planning objectives to obtain a planning-shaped future latent representation. Hindsight-to-Foresight Distillation trains a prior branch that depends only on history to predict this future latent representation. The predicted future latent representation serves as planning context and guides trajectory generation and selection. PlanWAM achieves 93.8 PDMS / 90.9 EPDMS on NAVSIM-v1/v2 navtest and reaches 38.7 HD-Score on closed-loop HUGSIM in a zero-shot setting, demonstrating leading planning performance across both open-loop and closed-loop evaluations. Extensive experiments further demonstrate that planning-shaped future representations provide an effective and deployable form of foresight for world-action models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11382
PDF
-
SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning
2026-10-08 06:40:18Wei Yang, Shawn Li, Yuehan Qin, Yawei Wang, Mingxi Wang, Shixuan Li, Tiankai Yang, Jiate Li, Jesse Thomason, Xuezhe Ma, Yue ZhaoAbstract
Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing this promise requires not only updating the agent, but also evolving its training experience as its capabilities change. However, most existing pipelines rely on static datasets or separately updated synthesis models, causing previously useful tasks to become trivial while overly difficult tasks remain uninformative. This growing mismatch between agent capability and training experience limits sustained self-improvement. To address this problem, we propose SynCo, an agentic data synthesis co-training framework for self-evolving LLMs based on multi-agent reinforcement learning. SynCo jointly optimizes two independently parameterized agents: a Synthesizer that constructs training tasks from the Reasoner's evolving capability state, and a Reasoner that learns from the resulting experience. Each synthesized task induces multiple Reasoner rollouts whose outcomes provide complementary rewards to both agents. Correctness feedback improves the Reasoner, while task quality, answer reliability, and outcome-grounded teachability guide the Synthesizer. Their updates are fed back into subsequent synthesis rounds, allowing the task-solving policy and its training distribution to evolve together. Extensive experiments across eight mathematical reasoning benchmarks demonstrate that SynCo substantially outperforms a broad range of existing synthetic-data methods and controlled baselines, achieving the strongest overall performance while deriving most of its gains from previously unsolved problems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11345
PDF
