AI Dataset2026
Contains a sanitized Claude Code (Fable 5) JSONL transcript of a session that procedurally built a Boeing 747 in Three.js, including assistant messages, tool calls, and base64 screenshots — useful for studying agent trace, tool use, and vision self‑verification workflows.
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.
AI Agent Papers2026
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.
AI Video Papers2026
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.
AI Agent Papers2026
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.
AI Agent Papers2026
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.
AI Agent Papers2026
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.
AI Agent Papers2026
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.
AI Model2026
A quantized 27B coder LLM fine-tuned for repository-level code generation, multi-turn tool calling, and agentic workflows — packaged for local GGUF/llama.cpp deployment with MTP speculative decoding and trace-inversion SFT. Optimized for developer tooling; experimental and not fully safety-validated.
AI Dataset2026
Anonymized agent-trace JSONL capturing conversations, tool calls, and function schemas from Claude fable-5 (Claude Code) runs — packaged for fine-tuning, distillation, and building tool-aware assistants; compatible with teich for conversion to OpenAI-style chats.
AI Dataset2026
Collects raw coding-agent sessions—developer prompts, model replies, tool calls, and command output—donated from public repositories and anonymized locally. Organized by agent harness (raw session files + Parquet table), useful for studying agent behavior and tool use; anonymization is best-effort.