Tag

Lets an AI agent propose, run, and evaluate multi-step research experiments using a persistent Hypothesis Tree that links hypotheses, artifacts, evidence, and distilled insights. Combines a long-lived coordinator with short-lived executors to carry lessons across time; evaluated on six ML tasks.

Synthesizes shortcut-resistant search tasks to train deep search agents by controlling four shortcut risks across entity selection, evidence-graph construction, question formulation, and adversarial refinement. Produces training trajectories with longer pre-answer search and fewer shortcut patterns; code will be released on GitHub.

Benchmarks evolving environments as sequences of progressive updates and introduces EvoMem, a patch-based memory that records structured update histories so LLM agents can reason about environment evolution. Demonstrates measurable gains on EvoArena and other benchmarks.

Provides a training-free, code-as-action framework that lets VLM-backed agents write and run stateful Python cells to compose perception and geometry primitives for open-ended 3D/4D spatial reasoning. Demonstrates consistent gains across 20 benchmarks and multiple VLM backbones.

Adds interleaved text–image generation to existing image generators via a multi-agent pipeline: a planner sequences stepwise instructions, a critic detects and refines failures, and single-step RL (GRPO) reinforces per-step corrections—suited for visual narratives and embodied guidance.