AI Agent Papers2026
Presents Jeva, a decision-native architecture that encodes requests and each candidate separately to produce permutation-invariant, option-scalable probability distributions with explicit null detection and reusable option representations for low-latency decision tasks.
AI Agent Papers2026
Chuyang Wei, Haoxiang Guan +6Affiliation: Zhongguancun Academy, Affiliation: University of Science and Technology of China +2
Defines a feedback-driven lifecycle that lets an agent's harness (prompts, memory, workflows, tools, control logic) iteratively self-revise across runs while keeping model weights fixed. Distinguishes interpreted vs executable updates, frames search as evolutionary, and gives a fresh-validation admission rule.
AI Agent Papers2026
Yuchen Lu, Julian McAuley +1Affiliation: University of California San Diego [email protected] [email protected] [email protected]
Organizes long-horizon agent continuation around reusable task objects — builds context from continuation carriers, execution context, and a live tail to preserve usable progress and reduce token/cost while improving task performance on long-horizon benchmarks.
AI Agent Papers2026
Evaluates whether long-horizon agents can complete real-world business requests while preserving valid intermediate execution. Built from 50 multi-turn payment workflows with 789 knowledge documents and 601 discoverable tools, and uses deterministic checks for process and protection violations.
AI Video Papers2026
Compiles a screenplay into shot requests annotated with explicit location, camera and event-time references to enable spatially and temporally consistent long-form agentic video generation. Uses a scene memory of registered geometry and an event memory of time-indexed observations, reconstructs and registers clips, and only admits updates after review and state checks to reduce cross-shot drift.
AI Dataset2026
Benchmark package for evaluating visual agents that produce editable 3D Blender projects from real-world text, image, and video briefs; includes 223 tasks, 2,651 binary rubrics, Harbor-compatible inputs with Base64 previews, and multi-view render verification.
AI Agent Papers2026
Provides an open release and system design for generalist computer-use agents (GCUAs), combining code execution, GUI actions, a real-device harness, and a cross-device SDK. Ships evaluation trajectories for multiple frontier models and shows large score and efficiency gains on OSWorld-v2.
AI Agent Papers2026
Benchmark for evaluating agents' ability to deliver working AI systems in realistic customer environments: 95 end-to-end delivery tasks with scripted stakeholders and production-like systems, scored by improvement to the customer's business metric and penalized for stakeholder contact.
AI Agent Papers2026
Alternates harness and policy optimization so a coding agent uses its own policy to propose harness revisions that target evolving failure modes. Combines harness search (H-step) with RL-based policy updates (P-step), improving resolve rates on multiple coding benchmarks and generalizing out-of-distribution.
AI Agent Papers2026
Provides a training-free multimodal reasoning harness that combines heterogeneous visual tools, persistent multimodal memory, and code execution so MLLMs can iteratively acquire and compose grounded evidence. Improves accuracy on 22 benchmarks by about 9.7–12.6 points while cutting comparative token costs.
AI Coding2024
Turns plain-language prompts into working websites, web apps, and mobile apps in the browser. Chat-driven code generation, live preview, hosting, databases, and GitHub/Figma imports help builders move from idea to shipped project without local setup.
AI Coding2024
Turns plain-language app ideas into working software inside a browser workspace, then lets users preview, debug, and deploy without leaving the platform.