Category

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Proposes “Graph Engineering”: using explicit, dynamic graphs to represent tasks, agents, tools, and system state so LLM-based agent systems can coordinate, persist, and evolve. Surveys principles, methods, applications, and curates related resources.

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Assesses mobile planning agents' ability to call tools, plan long-horizon workflows, and coordinate sub-agents in realistic, interactive phone scenarios via a stateful executable sandbox. Covers 13 domains, 212 tools, evidence-based verification, and tests memory, skill usage, permission and runtime constraints.

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Automatically optimizes runtime harnesses for LLM agents by diagnosing failure traces and iteratively applying structured, generalizable patches. Combines batch-based failure diagnosis, code-like patch generation across prompts/tools/middleware, and validation-aware selection to raise long-horizon task success on multiple benchmarks.

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Develops methods to scale agentic AI for sustained, verifiable execution of complex long-horizon work by expanding executable environments and training coordinated agents with a shared execution harness (AgentOS) to maintain state, provenance, and failure recovery.

FrontierChallenge: Evaluating Scientific Workflow Completion

Evaluates AI agents' ability to complete end-to-end scientific workflows by releasing and assessing 97 tasks from a 300-task FrontierChallenge suite across chemistry, materials, life science, and electrochemistry. Finds that top agent configurations achieved only a 20.6% pass rate despite high partial scores, revealing a gap between partial progress/confident completion claims and actual complete scientific deliverables.

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Proposes Recuris, a recursive Experiential-Working Memory architecture that separates Working Memory (task progress) from Experiential Memory (skills) and uses a Meta-Agent to validation-gate localized skill updates, enabling bounded recursive skill evolution for long-horizon agents.

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Proposes treating game development as a recursive data engine and introduces RLHEV (Reinforcement Learning with Human-Engine Verification) to combine dense engine checks (collision, physics, navigability) with human acceptance feedback, producing trajectory data and rewards for post-training world models.

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Synthesizes, repairs, and self-evolves task-adaptive agent harnesses on demand for off-the-shelf LLM agents, using a trainable harness-intelligence model that distills signals from past configurations. Demonstrates consistent performance gains across benchmarks and model families by producing four-module, composable harnesses.

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Analyzes how to generate useful interaction data for LLM agents and proposes the ACE lens — Accuracy, Complexity, divErsity — while factorizing agentic data as (E, q, τ, v). Surveys verification, difficulty calibration, and coverage strategies and outlines implications for training and benchmarks.

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Provides a real-scale 3D Hong Kong sandbox to evaluate whether multimodal LLM agents can turn local street-view perception into sustained spatial action, supporting closed-loop first-person interaction, an interactive map, and controlled tests of grounding, long-range navigation, and robustness.

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Decides when past post-training updates should be reused for autonomous LLM adaptation by introducing Boundary-Calibrated Intervention Transfer (BCIT). BCIT binds effects to source context, checks applicability and hard conflicts, and runs bounded trials to obtain current-state evidence—reducing harmful updates and improving equal-budget final-model quality.

UI-Venus-2 Technical Report

Autonomous multimodal GUI agent that executes natural-language interface tasks across mobile apps, web domains, and desktop OS. Expands environment coverage (170+ multilingual apps, 4,000+ web domains), uses function-grounded task generation and keypoint-based multi-model verification to produce reliable RL rewards for real-world deployment.