lets LLMs improve by revising the natural-language skill they follow. Existing methods use one trajectory per question, which makes it hard to tell which actions caused failure or success. SkillCome instead samples multiple trajectories per question, separates successful from failed ones, and contrasts them to isolate behavioral differences that matter. A dual-memory component accumulates evidence across historical steps, so the optimization direction is less swayed by noise in a single batch. On six benchmarks covering QA, reasoning, and agentic tasks, SkillCome outperformed baselines across five models of different families and scales, with gains up to +5.69 points.
Contrasting multiple trajectories sharpens skill learning for LLMs
SkillCome generates several attempts per question and compares them to identify what separates success from failure, then stores patterns across rounds in a dual memory.
Chinese Tech
Haolin Li · Feng Hong · Ang Li · Chilin Fu · Weichang Wu · Ya Zhang · +3 more
Fudan University · Ant Group · Shanghai Jiao Tong University
Research Digest··3 min read
Thread:Agent Self-Improvement
In one line
SkillCome improves skill evolution for language models by contrasting multiple successful and failed trajectories and using dual memory to derive reusable skills.
Before you read this
Three ideas this paper builds onskill evolutionThe process of developing, refining, or optimizing reusable capabilities in LLM agents through learning, adaptation, or experience accumulation.42 papers →agent memoryA repository where an agent stores past interactions and outcomes to inform future decisions.241 papers →agent skillsLearned capabilities that enable AI agents to perform specialized tasks with improved effectiveness.120 papers →
Read it as
Li et al. propose SkillCome, a method that improves large language models by iteratively refining textual skills.
The authors tested SkillCome on six benchmarks: GSM8K, MATH, CSQA, MuSiQue, SpreadsheetBench, and WebArena.
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.