Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2609.18542v1 Announce Type: new Abstract: 4D radar has emerged as a promising next-generation sensor for improving the robustness of autonomous driving perception systems because of its stable...
arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly...
arXiv:2609.18623v1 Announce Type: new Abstract: State-of-the-art vision-language-action models (VLA) for autonomous driving face critical limitations: excessive parameter counts, inefficient high-res...
arXiv:2609.19138v1 Announce Type: new Abstract: Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations...
arXiv:2608.00800v2 Announce Type: replace Abstract: Injection molding is the cornerstone of mass-producing plastic components. While current algorithms can automate mold design for basic geometries u...
arXiv:2609.17628v1 Announce Type: cross Abstract: Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to ta...
The paper introduces EvoSkill-GUI, a training‑free framework that enables GUI agents to evolve their skills during deployment. Each skill is packaged with metadata, executable plans, and recovery rules, and the system follows a reflect‑revise‑reuse loop where the agent instantly revises skills based on execution feedback. Experiments on MobileWorld, AndroidWorld, and OSWorld show consistent performance gains up to +16.2% without any additional training.
The paper introduces Composite‑Gradient Learning (CGL), a method that explicitly incorporates a model predictive controller (MPC) into the training of a deep reinforcement learning (DRL) agent by treating their control inputs as a joint action. CGL updates the DRL policy while accounting for the interaction with the MPC, unlike prior approaches that view MPC merely as part of the environment. Experiments on two freeway traffic networks show that CGL performs better than alternative methods when the interaction between DRL and MPC is strong, though overall gains are modest.
Delphos is a multitask reinforcement learning framework that automates discrete choice model specification by treating it as a sequential decision-making problem. It learns transferable specification strategies across multiple transport choice datasets using a DeepSet‑Q architecture, enabling a shared policy to adapt to varying variable sets. Trained on nine datasets, Delphos outperforms single‑task agents, and when applied to unseen Swissmetro and Decisions datasets, it quickly identifies competitive specifications with higher log‑likelihoods than existing methods.
The paper extends the concept of social laws from deterministic, goal-based multi‑agent systems to stochastic, reward‑based environments. It introduces a formalism for defining and verifying the robustness of these laws, including a new metric called α‑robustness that quantifies the utility each agent can guarantee while following the law. The authors present a verification approach that reduces the problem to solving multiple Markov decision processes and demonstrate the framework’s potential through empirical evaluations on toy environments.
StableEval Arena is a cost‑aware benchmark framework designed to evaluate agentic AI systems on stablecoin peg‑risk prediction. It tests LLM‑backed agents by diagnosing peg stress and forecasting deviations from the one‑dollar peg over a hidden seven‑day horizon, using leakage‑safe historical replay with exchange price‑volume data and market‑context features. The benchmark includes a 120‑case stress‑enriched validation block and a 507‑case natural‑distribution full‑arena evaluation, measuring prediction quality, calibrated‑label behavior, structured‑output reliability, latency, token consumption, and estimated inference cost across six LLM‑backed agent configurations and baselines.
The paper introduces PACT, a benchmark designed to evaluate how well enterprise AI assistants follow compliance rules when faced with various pressures such as persistent users or hurried managers. PACT covers twelve regulated domains and forty-eight realistic multi‑turn scenarios, pairing each rule with a shortcut that violates it and applying different pressures across wording and system‑prompt modes. Using PACT, the authors profile six metrics of compliance and aggregate them into a PACTScore, revealing significant variability among 22 LLM models and that even top performers misapply rules 6–10% of the time, with user pressure increasing violations by 65% on average.
The paper argues that agentic systems waste time and memory by guessing how long tool calls will take, rather than using explicit progress signals from the tools themselves. It demonstrates that tools can report their remaining work or imminent completion, and that incorporating this feedback into serving systems dramatically improves cache decisions and reduces token latency. The authors show that this approach outperforms existing predictors and works robustly across different environments.
The paper demonstrates that autonomous AI agents (rApps) in an O-RAN control plane can independently close control loops over shared radio resources, leading to unsafe interactions when multiple agents pursue different objectives. The authors introduce AURA, a lightweight arbitration layer that enforces feasibility invariants, dwell times, and a deadband to ensure stable operation. Implemented on an OpenAirInterface testbed, AURA reduces shared-state excursions by more than an order of magnitude and virtually eliminates cross-slice throughput starvation while maintaining latency compliance for the protected slice.
MIRAGE is a controlled study that examines how multimodal personal agents use historical evidence when conversation state changes. The study keeps evidence, questions, and scoring constant while varying only the conversation state, then checks if agents can determine answerability, recover the correct source, and answer from it. Results across seven multimodal backbones show distinct failure regimes before and after compaction, heavy reliance on context continuity by open-weight models, and mixed effects of retrieval pressure on source attribution.
The paper introduces LM Fight Arena, a new benchmark that pits large multimodal models against each other in the fighting game Mortal Kombat II to evaluate real‑time visual understanding and sequential decision‑making. Six leading open‑ and closed‑source models were tested in a controlled tournament where each controlled the same character, ensuring a fair comparison. The framework offers a fully automated, reproducible, and objective assessment of an LMM’s strategic reasoning in a dynamic setting.
The paper introduces AgenticDomiKnowS (ADS), a framework that converts free‑form task descriptions into fully functional DomiKnowS neuro‑symbolic programs. ADS employs an agentic workflow that builds and tests each DomiKnowS component independently, optionally allowing human‑in‑the‑loop refinement. The authors demonstrate that ADS enables both experienced and novice users to create complete neuro‑symbolic programs in 10–15 minutes, compared to the hour required for manual coding.
EvoUndo is a framework that enables large language model agents to self‑evolve—modifying prompts, tools, and execution harnesses—while ensuring that these changes can be reliably reversed across different states. The study evaluates EvoUndo on 600 unseen one‑shot self‑evolution tasks, finding that 197 capability‑improving mutations fail recoverability checks. By extending the recovery language and adding exact state‑address diagnostics, the framework recovers up to 191 out of 197 failures, demonstrating that robust self‑evolution requires co‑designing verification, grounding, witness semantics, and recovery expressivity.
The paper examines the rapid growth of the OpenClaw AI agent’s public skill registry, noting a near doubling of the observable stock in 91 days and a concentration of activity in a short period. It finds that only a small fraction of skills receive significant attention—most have no stars or comments—while a large portion contains privilege‑evident code. Automated security scanners show low agreement and sensitivity, indicating that current tools are insufficient for reliable governance of fast‑expanding agent‑skill ecosystems.
RideWay is a new benchmark that evaluates ride‑hailing language agents not just on task completion but on interaction efficiency. It introduces the Efficiency Utility metric, which penalizes agents for excessive tool calls and user‑facing turns relative to a task‑specific reference effort, with human preferences used to calibrate the penalties. Across 58 tasks and 24 models, the metric shows that extra dialogue is penalized more heavily than extra tool use, and it achieves high accuracy in distinguishing trajectories that differ in turns but struggles when differences are only in tool calls.