Transforms scientific code repositories into executable, agent-learnable environments that support task generation, execution, and scientific verification. Agent-guided repository transformation produces verified interaction trajectories used to train the PhAI-IDE model family. Intended for research on agent learning, scientific-code repair, and training RL/SFT models.
Extracts replayable behaviors from working web apps and converts them into verifiable, reference-guided software-engineering tasks to evaluate and diagnose coding agents; includes an automated pipeline that scales to thousands of tasks.
Finds token- and API-cost-saving harness mechanisms for long-horizon coding agents using automated recursive self-improvement; packages four surviving mechanisms (action fusion, context compaction, observation archiving, delegated reading) to cut recorded token traffic ~44.7–49.0% and API cost by about one third while preserving most capability.
Measures how individual harness components—planning, action space, and context management—affect coding agents' success, cost, and behavior. Uses a modular harness across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1 to isolate component effects and surface model- and budget-dependent trade-offs.
Provides reproducible, multi‑platform environments and execution‑grounded verification for hybrid computer‑use agents that interleave GUI exploration and code/CLI. Key features: a five‑platform harness, RecreationBench (250 tasks), reference‑grounded programmatic and visual assertions for automatic scoring.
Turns implemented functionality in open-source codebases into executable RL training environments by automatically generating behavioral specifications, execution-grounded tests, and post-rollout filtering; yields 5,545 verifiable coding tasks across 23 languages to train coding agents.
Uses a compact discrete-action interface (translation, rotation, gripper) to let frozen vision–language models control robots in closed-loop, and leverages in-context (one-shot) demonstrations to substantially improve manipulation success without robot-specific training.
Provides a unified benchmark and a spatially aware omni-modal model for spatial audio-visual reasoning in embodied agents — OmniEchoBench (197 scenes, 2,972 QA pairs; 900 FOA-based navigation tasks) plus OmniEcho, which adds an FOA spatial encoder to a pretrained semantic audio pathway to enable spatial QA and sound-guided navigation.
Provides a unified data and evaluation suite for measuring gameplay capabilities across short, medium, and long temporal horizons. Includes an automated annotator, a 5,000-hour AAA gameplay dataset with temporally aligned frames, actions and multi-horizon instructions, and a reproducible offline + stepwise online benchmark.
Edits an LLM agent's internal task state and action continuations to remove unsupported assumptions and noisy plans, improving downstream decisions instead of reconstructing high-entropy tool outputs. Combines Action Judge, State Revision, and EditAct and shows consistent gains across benchmarks and agent backbones.
A mobile-planning agent paper that develops a closed-loop AI-for-AI lifecycle to generate data, train a planner model, and co-evolve a runtime Harness for multi-app task execution. Demonstrates top performance on MobilePA-Bench with improved tool use, memory, skill coordination and low estimated per-task output cost.
Alternates a Planner (issues sub-queries) and a Synthesizer (integrates retrieved evidence into a persistent summary) to tackle long-horizon deep-search; introduces Role‑Decoupled Policy Optimization (RDPO) for role-specific RL credit assignment and shows strong results (IterSynth-8B reaches 50.7% on five benchmarks).