[KongchangAI]
Paper协作引导的轻量级故障归因

CoLFA

A lightweight fault attribution method for multi-agent systems. It organizes input using collaboration cues such as handoffs and cross-references to precisely locate erroneous steps and responsible agents at low token cost.

Timeline (last 90 days)

Nov 13

CoLFA is a lightweight multi-agent fault attribution method guided by collaborative cues, which organizes attribution inputs by leveraging collaborative cues.

Unverified50%
Nov 13

CoLFA achieves lightweight attribution through two key techniques: Handoff-Guided Step Expansion and Cross-Referenced Content Organization.

Unverified50%
Nov 13

On the two datasets Who&When and LongRCA, across five settings and three backbone models, CoLFA achieved the highest exact step localization accuracy while consuming the fewest tokens.

Unverified50%
Nov 13

Compared with the individual baselines under each setting, CoLFA improved exact step localization accuracy by up to 37.50%.

Unverified50%
Nov 13

Compared with the individual baselines under each setting, CoLFA reduced token consumption by up to 97.6%.

Unverified50%

All Facts (5)

Source Articles