Experience Memory Graph: One-Shot Error Correction for Agents

• URL: http://arxiv.org/abs/2607.13884v1
• Date: Wed, 15 Jul 2026 14:33:15 GMT
• Title: Experience Memory Graph: One-Shot Error Correction for Agents
• Abstract summary: Large Language Model (LLM) agents suffer from compounding errors and struggle to recover from failures.<n>Existing self-correction mechanisms rely on prompt-based reflection, which is inherently brittle.<n>We propose Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem.
• Score: 9.23684438376937
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from failures. Existing self-correction mechanisms rely on prompt-based reflection, which is inherently brittle, incurs heavy time and API costs due to iterative trial-and-error loops, and produces task-specific memory that may be hard to generalize to new scenarios. To address this, we propose Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem. At training time, we convert both failed exploration trajectories and successful expert trajectories into directed action decision graphs. By matching these graphs, we extract common subgraphs (successful workflows) and graph edit paths that explicitly indicate how to correct failures (e.g., which actions to add, delete, or relabel under a given observation), and store them in a memory graph with intra-task nodes and cross-task edges. At test time, EMG retrieves relevant insights and guides the agent in a single, loop-free execution. Experiments on ALFWorld and ScienceWorld show that EMG consistently outperforms state-of-the-art reflection baselines in success rate and average reward, while requiring no test-time trial-and-error.

Related papers

• Procedural Graphs: Self-Evolving Execution Structures for LLM Agents [11.810729293911622]
  Procedural Graph organizes procedural knowledge into (procedure, relation, procedure) triplets for what-to-do questions.<n>At each decision step, the framework localizes the agent's active node, and a guidance model translates the surrounding subgraph into step-level situational guidance.<n>The graph is self-evolving: an LLM refiner contrasts failed trajectories with successful ones and edits the graph's topology and attributes.
  arXiv  Detail & Related papers  (2026-09-08T17:59:41Z)
• EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems [16.87029422280475]
  We introduce EDGE, an Error Dependency Graph-guided multi-Error attribution framework.<n>We show that EDGE improves category-level multi-error attribution across most evaluated models and settings.
  arXiv  Detail & Related papers  (2026-09-01T15:00:54Z)
• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems [16.78530745432555]
  We introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that transforms a failed trace into a structured graph and then navigates it to identify the critical error.<n>Across multiple models, we show that richer trace representations consistently improve failure attribution.<n>This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored.
  arXiv  Detail & Related papers  (2026-08-25T10:18:19Z)
• TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories [48.638067300108276]
  Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure.<n>Long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context.<n>We propose Traj Debug, an error-lifecycle tracing framework that addresses long-trajectory error discovery.
  arXiv  Detail & Related papers  (2026-08-06T17:51:20Z)
• Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems [47.66236392009794]
  Large Language Model(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks.<n>We propose textitTrajectory Graph Copilot, a novel framework that acts as a copilot'' for LLM agents by diagnosing potential action errors before they are executed.
  arXiv  Detail & Related papers  (2026-07-29T20:14:43Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Atomic Task Graph: A Unified Framework for Agentic Planning and Execution [13.978062792065215]
  Atomic Task Graph (ATG) is a unified control framework for planning and execution.<n>ATG maintains an explicit graph to expose dependencies and support reuse.<n>ATG consistently outperforms strong baselines in success rate and execution efficiency.
  arXiv  Detail & Related papers  (2026-07-02T09:34:20Z)
• AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents [50.481033105867205]
  We introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories.<n>The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement.<n>It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity.
  arXiv  Detail & Related papers  (2026-03-15T16:13:58Z)
• TIMID: Time-Dependent Mistake Detection in Videos of Robot Executions [39.788348066726826]
  A new VAD-inspired architecture, TIMID, is able to detect robot time-dependent mistakes when executing high-level tasks.<n>Our architecture receives as inputs a video and prompts of the task and the potential mistake, and returns a frame-level prediction in the video of whether the mistake is present or not.
  arXiv  Detail & Related papers  (2026-03-10T15:17:34Z)
• AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning [34.06688334066569]
  AgentDropoutV2 is a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining.<n>Our approach acts as an active firewall, intercepting agent outputs and employing a retrieval-augmented to iteratively correct errors.<n> Empirical results on extensive math benchmarks show that AgentDropoutV2 significantly boosts the MAS's task performance.
  arXiv  Detail & Related papers  (2026-02-26T17:31:43Z)
• ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration [68.89572566071575]
  ETAgent is a training framework for calibrating agent's tool-use behavior.<n>It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors.
  arXiv  Detail & Related papers  (2026-01-11T11:05:26Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• Where LLM Agents Fail and How They can Learn From Failures [62.196870049524364]
  Large Language Model (LLM) agents have shown promise in solving complex, multi-step tasks.<n>They amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions.<n>Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way.<n>We introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations.
  arXiv  Detail & Related papers  (2025-09-29T18:20:27Z)
• FVDebug: An LLM-Driven Debugging Assistant for Automated Root Cause Analysis of Formal Verification Failures [8.530369312832084]
  We present FV Debug, an intelligent system that transforms failure traces into actionable insights.<n>Our approach features a novel pipeline: (1) Causal Graph Synthesis that structures failure traces into directed acyclic graphs, (2) Graph Scanner using batched Large Language Model (LLM) analysis with for-and-against prompting to identify suspicious nodes, and (3) Insight Rover leveraging agentic narrative exploration to generate high-level causal explanations.
  arXiv  Detail & Related papers  (2025-09-16T20:22:10Z)
• GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval [3.792463570467098]
  GraphRunner is a novel graph-based retrieval framework that operates in three distinct stages: planning, verification, and execution.<n>It significantly reduces reasoning errors and detects hallucinations before execution.<n>Our evaluation using the GRBench dataset shows that GraphRunner consistently outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-07-11T18:10:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.