#tool-use
9 articles
01
·Agents·★ MEMBER·PAPER·13 min read
Paper Explained: StarHarness — Evolving the Scaffold Instead of the Weights
Freeze the model weights and search over the harness instead — prompts, tool schemas, skills, MCP providers, subagents, agent loop. Across three enterprise benchmarks this bought 20–35 points, held on tasks never used for evolution, and transferred to other models unchanged.
02
·Distillation & Compression·★ MEMBER·PAPER·10 min read
Distilling Agents — How to Compress a Long Trajectory
When you distill an agent, the unit of learning changes from a single question-and-answer to an entire game. Tens of thousands of tokens come back with one bit of grading. This article works through how that gap is bridged — turn-level credit assignment, trajectory filtering and on-policy correction, and the inheritance of tool use — and maps the recent long-horizon agent literature onto those three axes.
03
·Agents·FREE·11 min read
MCP and Tool Protocols — The Standard That Connects an Agent's Hands
When an LLM touches your calendar or your database, what is actually wired to what? From what a tool call really is, to the N×M problem MCP solves, to designing tool definitions, to the security boundary you cannot design around — starting from zero.
04
·Agents·★ MEMBER·PAPER·8 min read
Build Your Own Agent Loop — The Minimal Shape of Tool Calling
At the center of every AI agent is a single while loop. We build it from scratch without a framework — the shape of JSON function calls, what ReAct actually left behind, and the stopping conditions where nearly every incident originates.
05
·Agents·★ MEMBER·PAPER·9 min read
Paper Explained: Video-DeepResearch — Agents That Watch a Video, Then Chase Down Every Lead
A walkthrough of Video-DeepResearch, which pulls visual clues out of a video and corroborates them with web search. We follow the primary source to see how two failure modes — a modality bias that makes models dodge visual tools, and knowledge leakage that lets them answer from memory alone — are beaten with stage-wise tool unlocking and a two-phase SFT + GRPO recipe.
06
·Agents·★ MEMBER·PAPER·8 min read
Paper Walkthrough: ToolArtist — Search, Draw, or Redraw? The Image Agent That Decides for Itself
Drawing "a harvester collecting dragon's blood resin on Socotra in 1955" correctly takes less artistic skill than research. ToolArtist makes searching, reasoning, and drawing all actions of a single policy — a fully agentic image generator. We walk through the conversion trick behind its SFT data, the dual-reward RL scheme (RAD-GRPO), and the 0.79 WISE result, straight from the paper.
07
·Agents·★ MEMBER·PAPER·8 min read
Paper Walkthrough: EnvACE — Agents That Rehearse the World Instead of Calling It
EnvACE trains a tool-using LLM agent without ever calling an external environment: the same policy alternates between acting and playing the environment. We walk through role-wise GRPO, test-time private rehearsal, results on four agent benchmarks, and the limitations.
08
·Agents·★ MEMBER·PAPER·8 min read
LLM Agents from Scratch — Designing the Tool-Use Loop
Think, reach for a tool, look at what came back, think again. Working only from the text of the ReAct paper (Yao et al., 2022): why adding language to the action space is the whole idea, what function calling really implements, and the failure modes the authors actually measured — runaway loops and hallucinated tool calls.
09
·Agents·★ MEMBER·PAPER·8 min read
LLM Agents from Scratch — Designing the Tool-Use Loop
Think, reach for a tool, look at what came back, think again. Working only from the text of the ReAct paper (Yao et al., 2022): why adding language to the action space is the whole idea, what function calling really implements, and the failure modes the authors actually measured — runaway loops and hallucinated tool calls.