cs.AIAug 25, 2026
SaveAdaptive Influence Graphs for Failure Attribution in Multi-Agent Systems
Organizations: Tel Aviv University · AWS Agentic AI
Abstract
Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing efforts to automate failure attribution, diagnosing failed runs still largely relies on human engineers. Yet engineers rarely debug complex systems by reading raw logs end to end. Instead, observability tools organize traces around components, actions, and dependencies to support targeted navigation. We hypothesize that modern LLMs can benefit from the same paradigm. To test this hypothesis, we introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that first transforms a failed trace into a structured graph and then navigates it to identify the critical error. Across multiple models, we show that richer trace representations consistently improve failure attribution, with adaptive graph construction and agent-directed traversal yielding the strongest results. AIGs establish a new state of the art on Who&When, the standard benchmark for multi-agent failure attribution. This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored.
Figures & tables
Figure 1: The same trace yields different attributions depending on its representation. The raw log highlights the visible symptom (step 3); the Adaptive Influence Graph traces the error back to its origin (step 2).
Figure 2: Step accuracy improves with richer trace representations, and improves further when the adaptive graph is traversed by an agentic reader (Algorithm-Generated Who&When, Opus-5).
Figure 3: Build-read pipeline for Adaptive Influence Graphs (AIGs). The builder uses log-inspection and graph-construction tools to produce ; a critic–refiner audits its structural and semantic validity; and a reader uses graph and log-inspection tools to produce the final attribution.
| Method | Model | Algorithm-Generated Dataset | Hand-Crafted Dataset | ||
| Step Acc. | Agent Acc. | Step Acc. | Agent Acc. | ||
| All-at-Once | Opus-5 | 46.40 | 67.20 | 22.41 | 50.00 |
| Step-by-Step | Opus-5 | 42.40 | 54.40 | 25.86 | 58.62 |
| CDC-MAS ( Ma et al., 2025 ) | GPT-4o | 36.00 | 48.50 | 18.20 | 56.80 |
| AgenTracer-8B ( Zhang et al., 2025a ) | Qwen3-8B | 37.30 | 63.73 | 20.68 | 63.82 |
| CORRECT ( Yu et al., 2025 ) | GPT-5 | 38.10 | – | 17.20 | – |
Table 1: Who&When benchmark. Rows use no ground-truth access at inference time. One Algorithm-Generated log is content-filtered by Opus-5; therefore, for this model we use . † Run using the authors’ released code. Our methods are shaded.
| Representation | Step | Agent |
| Raw log | 46.40 | 67.20 |
| Structured log | 48.80 | 63.20 |
| Influence Graph | 52.00 | 70.40 |
| Adaptive Influence Graph | 50.40 | 64.80 |
| Adaptive Influence Graph | 55.20 | 71.20 |
Table 2: Opus-5 representation ablations on the Algorithm-Generated Who&When partition (no ground-truth access). Our AIGs are in bold.
| Representation | Step Acc. | 1 | 2 | 3 |
| RAFFLES (Llama-3.3-70B) | 43.65 | 58.73 | 73.81 | 82.54 |
| Structured log | 48.80 | 60.00 | 72.00 | 80.00 |
| Influence Graph | 52.00 | 61.60 | 73.60 | 80.00 |
| Adaptive Influence Graph | 55.20 | 64.00 | 78.40 | 84.00 |
Table 3: Step accuracy under relaxed tolerance windows ( steps) on the Algorithm-Generated Who&When partition (Opus-5). RAFFLES results as published by the authors, who report tolerance windows only for Llama-3.3-70B.
| Property | AIGs | IGs | ||
| Nodes per graph | 9.5 | 2.0 | 7.5 | 2.2 |
| Edges per graph | 13.5 | 3.6 | 9.0 | 3.2 |
| Edge density (edges / node) | 1.4 | 0.2 | 1.2 | 0.2 |
| Max hub out-degree | 3.6 | 1.1 | 1.8 | 0.6 |
| Max steps merged into one node | 2.8 | 1.2 | 1.6 | 0.5 |
| Mean cross-range distance | 3.6 | 1.0 | 3.1 | 1.0 |
Table 4: Properties of the constructed graphs averaged across the Algorithm-Generated partition ( standard deviation across graphs).
Figure 4: The same trace encoded as an Influence Graph and as an Adaptive Influence Graph.
| Agentic reading profile | |
| First raw read is already | 61.3% |
| Opened steps within of | 48.4% |
| Multi-step investigation | 86.5% |
| Single-step verification | 11.9% |
| Commits from the graph alone | 1.6% |
Table 5: Reader behavior on the Algorithm-Generated partition (Sonnet-4, no ground-truth access). The last three rows partition executions by reading depth. is the step the execution submits.
Figure 5: Each panel highlights one move in orange; chords are inheritance edges and numbers are the raw-log steps a node merges. Rather than follow transcript order, the reader walks inheritance edges from the node the graph implicates, then commits to step 6, matching the annotation.
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
| Tool | Description |
| Inspection ( ) | |
| get_overview | Compact metadata about the log: step count, per-step agent, and sizes. |
| read_full_log | Return every step concatenated. |
| read_step | Return one step’s content. |
| read_step_range | Return an inclusive range of steps. |
| list_agents | List every agent and its system prompt. |
Table 6: Builder tools. Inspection reads the log ; construction edits the graph.
| Node type | Role & fields |
| task | The user’s question that seeds the trajectory—the root of the graph (no incoming edges). Fields: content (the question), operative_brief (the instructions the trajectory starts under), step_refs |
| orchestrator | A coordinating turn—an agent that plans, delegates, or judges progress and routes the work onward. Fields: agent_name , summary (what the agent did in this turn, start to end), authorship (as in agent ), step_refs |
| agent | A working turn—an invoked agent that executes a delegated instruction and produces a result. Fields: agent_name , summary , input (the instruction, context, or prior result it worked from), output (the concrete result, decision, tool output, or handoff it produced), authorship (whether it authored that output), defect_recorded (the node whose output fails the optional system-emitted instruction_or_question it was given, yet is committed downstream), step_refs |
| conclusion | The final answer the system produced—the terminal sink (no outgoing edges). Fields: content (the final answer), step_refs |
Table 7: Node types in the agentic graph. Every node carries step_refs , the raw-log steps it covers.
| Method | Model | Algorithm-Generated | Hand-Crafted | ||
| Step Acc. | Agent Acc. | Step Acc. | Agent Acc. | ||
| All-at-Once | Opus-5 | 44.00 | 63.20 | 18.97 | 51.72 |
| Step-by-Step | Opus-5 | 40.80 | 54.40 | 22.40 | 50.00 |
| FAMAS ( Ge et al., 2025 ) | Qwen2.5-72B | 23.81 | 55.56 | 41.38 | 62.07 |
| AgenTracer-8B ( Zhang et al., 2025a ) | Qwen3-8B | 42.86 | 69.62 | 20.68 | 69.10 |
| CHIEF ( Wang et al., 2026b ) | DS-V3.2 | 52.00 | 76.80 | 29.31 | 77.59 |
Table 8: Who&When benchmark with ground-truth access at inference time. Baseline numbers are as reported by their authors. One Algorithm-Generated log is content-filtered by Opus-5; therefore, we use for this model. † Run using the authors’ released code. Our methods are shaded.