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.
AI Agent2026
Orchestrates, composes, and governs multiple AI agents (Claude Code, Codex, Cursor, Pi, and custom agents) via a meta-harness that enforces policy-based sandboxing, spend caps, and live collaborative sessions. Agent behavior is declared in YAML and can run locally or in managed cloud sandboxes.
AI Model2026
An agentic multimodal coding model for long-horizon software tasks: MoE architecture (1T params, 32B activated), 256K context, image/video input, native int4 quantization and preserved chain-of-thought (thinking) mode. Tuned for multi-step coding workflows and vLLM/SGLang deployment.
AI Model2026
Provides experimental GGUF-format quantized weights for MiniMax-M3 to run local multimodal (image‑text‑video) inference via llama.cpp or Unsloth Studio. The model is very large (~428B params) and requires GPU offload or large CPU RAM; llama.cpp currently falls back from sparse to dense attention.
AI Model2026
Provides a locally runnable GGUF quantized build of Kimi K2.7 Code for multimodal, coding-focused agentic workflows — a 1T-parameter MoE model with 256K context, native int4 support, preserved thinking-mode, and image/video input support.
AI Agent Papers2026
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%.
AI Agent2026
Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.