Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2609.08196v1 Announce Type: new Abstract: This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a re...
arXiv:2609.06476v1 Announce Type: cross Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate unseen environments by following natural la...
arXiv:2609.09578v1 Announce Type: cross Abstract: Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical obje...
arXiv:2609.10092v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate be...
AgenticGen is a reward‑guided framework for generating advertising videos that splits the task into strategy selection and draft generation, allowing online business feedback to supervise each stage. It learns performance‑based rewards from accumulated online metrics and rubric‑based rewards aligned with human quality standards, then applies DPO and GRPO to refine policies. Offline tests confirm the reward models, and online A/B tests on TikTok show significant gains in CTR, CVR, and advertising value over a baseline.
arXiv:2609.09476v1 Announce Type: cross Abstract: In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, maki...
The study examines whether language models can accurately predict their own behavior by comparing self-reports to actual performance across nine behavioral tests. Results show that direct self-report is weak and only modestly improved when the model sees the exact items, while generic questions about AI agents yield similar predictive power. First-person framing biases reports toward underestimating harmful behavior, and fine‑tuning on a model’s own record improves narrow predictions but does not generalize.
arXiv:2609.10052v1 Announce Type: new Abstract: LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for pr...
arXiv:2609.10522v1 Announce Type: cross Abstract: Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains cha...
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state h...
The paper describes a production migration of a large-scale customer‑support conversational assistant from a single blended model to a Dynamic Response (DR) architecture. DR replaces the Qwen3‑235B‑A22B responder with a bounded ReAct orchestrator that selects typed tools and a smaller generator that writes from a validated context contract. The migration yields significant improvements: precision‑first entity selection boosts reservation selector precision from 8.3% to 89.1%, typed action IDs eliminate structured‑action hallucination, and hard‑escalation responses drop from 5.60% to 3.08%. Latency is reduced from 3.87 s to 2.24 s, GPU usage is cut by roughly one‑third, and self‑hosting cuts annual model‑serving costs by more than an order of magnitude.
arXiv:2605.13841v3 Announce Type: replace-cross Abstract: Voice agents are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses realistic conversatio...
arXiv:2605.21384v2 Announce Type: replace-cross Abstract: As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test...
arXiv:2609.08796v2 Announce Type: cross Abstract: Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop...
The technical report introduces Gander, an end‑to‑end model that integrates omni perception, real‑time interaction, and agentic capabilities into a single framework. Unlike traditional turn‑based systems, Gander continuously processes streaming inputs from video, speech, and text, enabling natural full‑duplex interaction in both everyday conversations and workflow‑oriented scenarios. Its architecture features a Cerebellum‑Brain collaboration—where the Cerebellum handles real‑time interaction and omni conversational tasks while the Brain manages complex reasoning—and a streaming Thinker‑Talker design that flattens inputs and outputs into an ordered token stream for low‑latency, continuous dialogue. Evaluations across conversational ability, omni understanding, interactive capability, and agentic intelligence show that Gander matches state‑of‑the‑art open‑source models in spoken dialogue while maintaining robust performance in noisy, multi‑party, and backchannel environments.
The paper investigates the use of variational quantum circuits (VQCs) in hierarchical reinforcement learning (HRL). It shows that a hybrid HRL agent incorporating a quantum feature extractor can outperform classical baselines with fewer parameters, but using VQCs for option-value estimation hampers learning. The study also explores how different quantum circuit designs influence performance and proposes design principles for efficient hybrid HRL agents.
arXiv:2603.04949v2 Announce Type: replace Abstract: As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We introduce...
arXiv:2609.07099v1 Announce Type: cross Abstract: We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the large-model division and second...
arXiv:2609.10377v1 Announce Type: cross Abstract: Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities...
arXiv:2609.09852v1 Announce Type: new Abstract: The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech intera...