DeFA converts a recorded agent trajectory into an event dependency graph.
Dependency graphs pinpoint decisive errors in long agent execution traces
DeFA reconstructs how mistakes propagate through agent trajectories to identify the responsible agent, decisive step and failure type.
Chinese Tech
Bo Deng · Xinlei Zheng · Yi Wei · Kang Zhou · Chongyang Tao · Renzhao Liang · +3 more
Qwen DianJin Team, Alibaba Cloud Computing · Beihang University
Research Digest··3 min read
Deng et al.
Why this paper
From Qwen DianJin Team, Alibaba Cloud Computing and Beihang University
In one line
DeFA achieves the highest accuracy in attributing decisive errors and responsible agents in LLM agent trajectories.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§