Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution

Summary

Addresses error attribution in LLM multi-agent systems - pinpointing which agent and which step caused a failure - and proposes ECHO, combining hierarchical context representation, objective analysis-based evaluation and consensus voting, reporting superior performance on subtle reasoning errors and complex interdependencies. A useful post-MAST citation for the measurement side of the paper: if failures can be attributed to specific agents and steps, traceability is measurable rather than rhetorical.

Contribution

Queued — not yet read.

Method

Queued — not yet read.

Relevance to RISE

Surfaced by the 2026-08-29 literature sweep as a medium-priority candidate for the Architecture as Epistemology (ISR) paper (angle: MAS failure and cost analyses; epistemic quality of LLM outputs). Verified against: Opened https://arxiv.org/abs/2510.04886 (arXiv abstract page, v2 16 Oct 2025)

Critique / open questions

Queued — not yet assessed.

Key quotes

Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. (abstract)

Current approaches to pinpointing agent and step level failures in interaction traces - whether using all-at-once evaluation, step-by-step analysis, or binary search - fall short when analyzing complex patterns, struggling with both accuracy and consistency. (abstract)