The paper introduces an acceptance protocol for sensor-coordinate and polarity binding in mechatronic commissioning, separating candidate generation from release authority. It routes unsupported requirements to a frozen four‑billion‑parameter local language model and only releases plans when both facts can be derived by an external gate under a sealed grammar, with a gold‑standard user providing a canonical answer when eligible. Evaluation on 144 tasks showed that fabricated plans were correctly rejected, no false releases occurred among 83 releases, and protection against incorrect user answers was characterized across 431 pairings.
The paper presents a graph-based framework for large-scale railway network management that combines a hierarchical Bayesian model with a Gaussian Process on a graph kernel to model spatially correlated maintenance environments, and a topology-aware Multi-Agent Reinforcement Learning system using graph neural networks and Transformers to optimize network-level policies. It demonstrates scalability by training agents on small network segments and deploying them zero-shot on larger, unseen networks, achieving superior performance over heuristics and standard MARL baselines while reducing training time. The approach addresses the computational challenges of centralized methods and the coordination gaps of decentralized methods in complex, long-horizon infrastructure asset management.
GRASP is a multi-stage planning framework that separates planning into specialized modules: GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation. This strategy-aware approach yields state‑of‑the‑art accuracy on diverse datasets, outperforming direct LLM planners by up to 30.8% on ZebraLogic and reducing multi‑task degradation. GRASP’s context isolation and macro‑regularization also give it a 14.5% edge over frontier reasoning models like GPT‑5‑mini.
KernelOPT is a multi-agent system that optimizes GPU kernels generated by compilers like PyTorch Inductor by treating compiled models as structured artifacts. It preserves vendor library calls and focuses on Triton sub-kernels, using five profiling-guided LLM agents and a four-gate verification cascade to filter and validate candidates. On 250 KernelBench problems, KernelOPT achieves geometric mean speedups of 1.40×, 1.15×, and 1.07× over torch.compile at different optimization levels.
The Era by Eon benchmark tests enterprise agents by presenting questions that specify answer rules and require code to compute answers from a company’s data. In the original benchmark, top models answered 22–25 of 27 questions, barely distinguishing performance. The updated benchmark adds eight templates that rely on hidden facts not explicitly stated in any question or document, forcing agents to infer information from indirect data. Twelve agents were evaluated, with the best achieving 18 of 24 correct answers, while the hardest questions—requiring selection among similar records—were answered correctly only 1 out of 84 attempts across all agents.
Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems introduces AgentX-Model, a dual-agent framework that links proposal development with model experimentation in business-defined sandboxes. The Research Agent drafts proposals from literature and findings, while the Model Agent runs multi‑round experiments, returning code, metrics, and open questions. The framework cycles through Reproduce, Follow‑up, Composition, and Diagnose actions, achieving high AUC gains and significant business metric improvements in online A/B tests.
The article titled "How to Maximize Your Coding Agent Subscriptions" discusses ways to get more out of your coding agent subscriptions. It was published on Towards Data Science and focuses on optimizing the use of these tools. The post offers practical tips and strategies for users to enhance their experience with coding agents.
By Eivind Kjosbakken
Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical reasoning can change future actions and the resulting interaction trajectory.
S2Planner is a trajectory planner for autonomous driving that fuses data from three front-facing cameras, ego‑motion history, and the current driving command. It uses a fine‑tuned DINOv3 backbone with a Spatial Tuning Adapter to generate multi‑scale image features, which are then refined by a coarse‑to‑fine decoder employing trajectory self‑attention and camera‑projected cross‑attention. The key contribution lies in integrating ego‑conditioned trajectory initialization with iterative, geometry‑guided sampling of multi‑scale image features, rather than introducing a new visual backbone or attention operator.
The paper introduces a dataset of the complete development history of a 21,000-line Python tool built entirely by Claude AI, accompanied by two code‑provenance tracing tools and three taxonomies for instruction intent, commit provenance, and response reliability. Analysis reveals that user CLI instructions differ from IDE‑chat instructions, focusing more on comprehension, planning, and consultation; code development is largely proactive; 14.3% of AI code‑generation events contain errors later caught by the AI‑authored test suite; and roughly one in four to five of the AI’s interactive responses contain factual errors.
Agentic-GER is an LLM-based agent designed to correct terminology in long‑form speech transcripts. It leverages global context from the full transcript to flag suspicious terms, selectively re‑transcribes the source audio to verify candidate corrections, and uses accepted edits to inform future decisions. Experiments on GigaSpeechBench with four LLMs and two ASR systems show consistent terminology improvements in both Chinese and English, achieving up to a 36.8% relative reduction in biased character error rate over the Whisper baseline.
HarnessPAI introduces a model‑ and embodiment‑agnostic harness framework for Physical AI that treats code as an executable, evolvable interface organizing action primitives. The framework operates on two timescales: within a rollout it executes an open‑loop program, and across rollouts it evolves a closed‑loop program using feedback to refine the program and distill reusable skills. Across diverse robotic platforms, HarnessPAI outperforms pure action models and code‑as‑policy baselines, achieving significant gains on tasks such as LIBERO‑PRO and RoboCasa, and enabling efficient expert‑data collection for further fine‑tuning.
The paper introduces SkillPivot, a framework that guides large language model agents to improve their natural-language skills by focusing on the point where a successful solution path deviates into an error. SkillPivot identifies this transition using execution validity, goal progress, and action diversity, then employs a stronger teacher to generate a successful alternative from the same prefix. By contrasting the failed and successful suffixes, the method produces localized, compact skill updates that preserve existing effective guidance and outperform other skill-evolution approaches on multiple benchmarks.
The paper examines on‑policy self‑distillation (OPSD) for multi‑turn agents, showing that using privileged information (PI) in the loss can make agents appear confident yet underperform plain RL, sometimes worse than the untrained base model. To address this, the authors propose Privileged Self‑Practice (PSP), which keeps PI in the prompt and uses it only during sampling, not in the loss. PSP consistently outperforms plain GRPO across AppWorld and SWE‑bench Verified, improving task‑goal completion by up to 65% and resolved rate by up to 61%.
FairTest is a search-based testing framework designed to uncover fairness failures in Multi-Agent Reinforcement Learning (MARL) systems. It guides candidate generation using three fitness functions—measuring observed fairness, predicting fairness from abstract states, and assessing policy decision uncertainty—and prioritizes tests based on predicted fairness and uncertainty. Evaluations on three environments and two MARL algorithms show FairTest detects significantly more fairness failures than three baselines, with a 221% increase in failure count and 23% better coverage on average.
By Xiaotong Wang, Xuan Xie
The paper introduces Latent Action Driving Annotations (LADA), a three‑stage pipeline that converts large amounts of unlabelled observation‑trajectory data into a language‑conditioned driving model. First, a latent action model with a vector‑quantised bottleneck learns a compact codebook of vehicle intents. Then, a small set of language‑annotated examples trains a vision‑language translator to map observations and instructions into this codebook, and finally a VLA is trained on observation‑latent‑action pairs across the full corpus. Using less than 5% of language annotations, LADA attains a Driving Score of 87.98 and a Success Rate of 70.46% on Bench2Drive, matching or surpassing fully supervised baselines.
By Alexey Zakharov, Kemal Oksuz, Puneet K. Dokania
The paper introduces LEAP-CBF, a safety filter that uses Least‑Effort Adversarial Potentials to quantify how much disturbance effort is needed to cause failure in nonlinear dynamical systems. LEAP serves as a control barrier function for the undisturbed system and can be combined with a robust safety filter that tolerates disturbances with bounded cumulative effort. The authors develop a deep reinforcement learning method to construct LEAPs and validate their effectiveness through simulations of multi‑agent systems and hardware experiments on a quadruped and quadrotors.
By Oswin So, Eric Yu, Chuchu Fan
ChronoSteer is a decoupled agentic framework that bridges large language models and time series foundation models by learning cross‑modal alignment from synthetic paired supervision. It converts textual events into revision instructions that steer a frozen time‑series model, discretizes these instructions into a compact codebook to reduce semantic divergence, and then refines the predictions with a two‑stage training strategy. The authors also release a leakage‑controlled multimodal benchmark and report a 25.8% improvement in zero‑shot prediction accuracy over the unimodal backbone.
By Chengsen Wang, Qi Qi, Zhongwen Rao, Lujia Pan, Jingyu Wang
The paper introduces Motion Vision CAPTCHA (MVCAP), a new CAPTCHA framework that relies on motion-defined foreground structures to create challenges that are only solvable through temporal analysis of a dynamic background. MVCAP is implemented in three progressive levels—coherent motion, structural motion, and biological motion—and evaluated using the MVCAP-Bench, a browser-based benchmark with 600 live CAPTCHA instances. Human participants achieve 99.6% accuracy, whereas the best GUI agent scores only 16.8%, highlighting a significant human–agent perception gap and demonstrating that dynamic background camouflage is the key difficulty.
By Zeyu Zhang, Dingyi Rong, Zijian Chen, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai
AstraLOD3 is a zero‑shot multimodal agentic system that reconstructs LOD3 building models using multi‑view images, calibrated cameras, a filtered sparse SfM point cloud, and a natural‑language specification. The Astra agent selects and executes computational steps in Python and Blender, achieving a mean FRDS of 0.9647 across 35 runs, including 24 benchmark buildings, with geometric agreement comparable to purpose‑built methods. Ablation studies show the impact of reconstruction guidance, evidence modalities, model configuration, and run‑to‑run variability, demonstrating that LOD3 reconstruction can be framed as a constrained agentic process rather than a fixed pipeline.
By Bryan G. Pantoja-Rosero