Category
Explore by categories
Turns raw datasets into verifiable multimodal news features via a multi-agent newsroom pipeline. Key innovations: (1) an Inspector that links each claim to data/code/external references for re-execution and audit; (2) multimodal asset generation (interactive maps, audio, visuals) tailored to the story.
Lets a single LLM simultaneously act as agent and environment to bootstrap co-evolutional training — using state-prediction process rewards (World-In-Agent) and failure-mode retrieval (Agent-In-World) to reshape training data; reports ~4% average benchmark gain.
Shifts branching and credit assignment in agentic RL from coarse units to fine-grained decision points in generated sequences. Uses a Branching Score combining token uncertainty and policy-induced likelihood gains plus procedure-level advantage scaling; improves performance across 13 benchmarks while keeping efficient tool calls.
Orchestrates teams of sub-agents across text, image, audio and video by modality-aware task decomposition, online sub-agent specialization, and parallel execution; introduces DA-GRPO to train Orchestra-o1-8B and reports a ~10.3% accuracy improvement on the OmniGAIA benchmark.
Continuously watches live video and autonomously decides each second whether to speak, stay silent, or delegate; released together with an 8B vision-first model, time-aligned interaction data, training recipe, and a deployable real-time system. Designed for vision-triggered, low-latency streaming scenarios and evaluated across six real-world streams.
Survey of methods for engineering interactive environments for LLM-based agents, covering environment modeling, symbolic and neural synthesis, evaluation, and agent–environment co-evolution. Identifies evolution paradigms and future directions like Environment-as-a-Service and multi-agent systems.
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.
Moves repository search into a dedicated exploration subagent that issues parallel read-only READ/GLOB/GREP calls and returns compact file:line citations. Trained (4B–30B) with SFT+RL, it reduces main-agent token use up to ~60% and raises end-to-end success by up to ~5.5%.