AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Failure Localization in Multi-Agent Code Generation via Knowledge-Guided and Transferable Reasoning

Mingyang Geng, Shanzhi Gu, Zhipeng Liu, Chuanfu Xu, Zhaoyang Qu, Haotian Wang

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Addresses failure localization in multi-agent LLM code generation using knowledge-guided and transferable reasoning (abstract only available).

Problem

Locating failures in multi-agent LLM code generation is hard due to inter-agent dependencies and multiple valid solution paths; existing prompting-based localization methods are vulnerable to semantically valid but non-canonical strategies.

Approach

Knowledge-guided and transferable reasoning for failure localization in multi-agent code generation; specific mechanism not stated in the available abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Knowledge Projection Module (ablation)FLKR · COFL general casesTop-1 LA (%): 58 -> 78Improved
add contextual divergence score (ablation)FLKR · COFL general casesTop-1 LA (%): 64 -> 78Improved
add knowledge divergence score (ablation)FLKR · COFL general casesTop-1 LA (%): 57 -> 78Improved
add InfoNCE contrastive alignment loss (ablation)FLKR · COFL general casesTop-1 LA (%): 60 -> 78Improved
add self-distillation loss (ablation)FLKR · COFL general casesTop-1 LA (%): 70 -> 78Improved
add Knowledge Projection Module (ablation)FLKR · COFL divergent-solution casesTop-1 LA (%): 43 -> 62Improved
add self-distillation loss (ablation)FLKR · COFL divergent-solution casesTop-1 LA (%): 52 -> 62Improved
replace prompting-based localization with FLKRBinary Search Prompting · COFL general casesTop-1 LA (%): 35 -> 78Improved
replace prompting-based localization with FLKRBinary Search Prompting · SoftwareDev out-of-domainTop-1 LA (%): 30 -> 76Improved
increase training data (ablation)FLKR · COFLFLA / Top-1 LAImproved
set distillation weight lambda near 0.7 and temperature 0.07-0.08 (ablation)FLKR · COFLFLA / Top-1 LAImproved

Limitations

Experimental setup

Baselines: prompting-based localization methods

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy