ai-models - The LGTM (Page 10)

The LGTM

Sign in Subscribe

ai-models

A collection of 177 posts

VibeSearchBench Shows Why Deep Research Still Misses What Users Actually Want

VibeSearchBench Shows Why Deep Research Still Misses What Users Actually Want

Most “deep research” benchmarks quietly assume the user has already done the hardest part: specifying exactly what they want. That is convenient for leaderboard construction and wildly unlike real work. Real users start with mush. They ask for a good vendor, a sensible travel plan, a market landscape, a replacement

SkillGrad Treats Agent Skills Like Code That Needs an Optimizer, Not a Pep Talk

Agent skills are being treated too much like helpful markdown and not enough like dependencies. That is the mistake SkillGrad is trying to correct. A skill can change how an agent edits a spreadsheet, reads a table, calls a tool, writes code, or follows a procedure. If that artifact can

MemTrace Turns Agent Memory Bugs Into Something You Can Actually Debug

MemTrace Turns Agent Memory Bugs Into Something You Can Actually Debug

Memory is where agent demos go to become production incidents. In a demo, the assistant remembers the user’s preference and everyone nods. In production, it stores the wrong preference, retrieves the stale one, overwrites the useful one, cites irrelevant history, and then produces an answer that looks confident enough

LearnWeak Makes Small Computer-Use Agents Better by Training on Their Actual Mistakes

LearnWeak Makes Small Computer-Use Agents Better by Training on Their Actual Mistakes

LearnWeak is a useful reminder that small agents do not need motivational posters. They need failure-specific training. The framework takes computer-use agents that are weak in particular desktop domains, finds where a stronger teacher succeeds and the smaller student fails, generates new tasks around those weaknesses, and trains the student

AXPO Shows Why Tool-Using Models Need Different RL Than Chat Models

AXPO Shows Why Tool-Using Models Need Different RL Than Chat Models

The interesting thing about AXPO is not that it makes Qwen3-VL-Thinking score a little better on multimodal benchmarks. The interesting thing is the failure mode it catches: models that know a tool exists, talk about using it, and then retreat back into pure text because acting has become too expensive