Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts

• URL: http://arxiv.org/abs/2607.01767v2
• Date: Sun, 05 Jul 2026 07:41:29 GMT
• Title: Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts
• Abstract summary: We study world-model correction: selecting a compact subgraph of a failed planning graph whose repair stabilizes subsequent rollouts.<n>We propose WM-SAR, a spectral subgraph repair method that estimates node-edge amplification.<n>We show that WM-SAR achieves stronger long-horizon stabilization and root-cause recovery under compact token budgets.
• Score: 2.571318992830046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon language agents increasingly maintain executable world models in the form of planning graphs, where tool calls, validators, memory updates, recovery branches, and final answers are connected by typed dependencies. When a rollout fails, repairing the most visible error can leave the underlying error-amplification path intact, while replaying the full graph is expensive and difficult for long-context models to use reliably. We study world-model correction: selecting a compact subgraph of a failed planning graph whose repair stabilizes subsequent rollouts. We first instantiate a strong family of engineering correctors, including pointwise error scans, TopK and window selection, local graph expansion, cascade repair, and full-context LLM repair. We then propose WM-SAR, a spectral subgraph repair method that estimates node-edge amplification, greedily grows a connected repair region by marginal residual-spectral relief, and sends only this region to an LLM for root-cause repair. Theoretically, we connect residual spectral radius to rollout error and planning regret, motivating repair as stabilization rather than attribution alone. Across synthetic calling-tree graphs, benchmark-inspired agent topologies, and cross-model LLM repair experiments, WM-SAR achieves stronger long-horizon stabilization and root-cause recovery under compact token budgets, matching much larger repair contexts while exposing the LLM to a cleaner causal subgraph.

Related papers

• 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)
• Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction [22.654396704495934]
  Development-set failures can recover part of the missing diagnostic substrate by deciding which recovery interventions are admissible.<n>We propose DARC, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment.
  arXiv  Detail & Related papers  (2026-08-12T08:14:45Z)
• Experience Memory Graph: One-Shot Error Correction for Agents [9.23684438376937]
  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.
  arXiv  Detail & Related papers  (2026-07-15T14:33:15Z)
• ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents [52.531681772560724]
  Supervised fine-tuning (SFT) is built mostly on successful trajectories and offers little signal for recovery after tool failures.<n>We introduce ReGRPO, a framework that learns reflection-guided correction in tool-using agents.<n> Experiments on GTA and GAIA show that, under the same backbone and tool suite, ReGRPO consistently outperforms strong open-source baselines.
  arXiv  Detail & Related papers  (2026-06-30T09:19:38Z)
• Adaptive Recurrent Message Passing for Test Time Computing on Graphs [80.56829418752513]
  We show that recurrent graph models can overcome the intrinsic mismatch between graph data and architectural designs.<n>We propose AdaR, an Adaptive Recurrent graph model, empowering flexible test-time computing on various downstream tasks without changing model parameters.
  arXiv  Detail & Related papers  (2026-06-21T12:14:11Z)
• Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version) [0.0]
  Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing.<n>Retrieval-augmented generation (RAG) systems have emerged as a common deployment scenario seeking to avoid the well known risk of the LLM "hallucinating" information.<n>In this work, we explore the idea of using a lightweight graph structure with a relatively simple graph schema, to support the RAG subsystem via a dedicated toolset.
  arXiv  Detail & Related papers  (2026-06-04T09:07:06Z)
• ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning [12.44509691077682]
  We introduce ANNEAL, a neuro-symbolic agent that converts recurring failures into governed symbolic edits of a process knowledge graph.<n>Its core mechanism, Failure-Driven Knowledge Acquisition (FDKA), localizes the responsible operator, synthesizes a typed patch through constrained LLM generation, and validates the proposal.<n>Across four domains and 27 multi-seed runs, ANNEAL is the only evaluated system that commits persistent structural repairs.
  arXiv  Detail & Related papers  (2026-05-04T05:24:03Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks [49.57538588967748]
  Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks.<n>We uncover a consistent phenomenon across modern architectures, including LLaMA, Qwen, and Gemma.<n>We show that symbolic reasoning failures in LLMs are not due to missing representations or insufficient scale, but arise from structured interference within the model's computation graph.
  arXiv  Detail & Related papers  (2026-04-01T11:40:12Z)
• GNNVerifier: Graph-based Verifier for LLM Task Planning [26.77252346424261]
  Large language models (LLMs) facilitate the development of autonomous agents.<n>Recent research has introduced plan verifiers to identify and correct potential flaws.<n>Most existing approaches still rely on an LLM as the verifier.<n>We propose a graph-based verifier for LLM task planning.
  arXiv  Detail & Related papers  (2026-03-16T02:05:21Z)
• AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs [15.570965946461255]
  Graph-based retrieval-augmented generation (RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge.<n>Existing methods face three critical challenges: Inaccurate Graph Construction; Poor Reasoning Ability; and Inadequate Answering.<n>We propose AGRAG, an advanced graph-based retrieval-augmented generation framework.
  arXiv  Detail & Related papers  (2025-11-02T06:13:06Z)
• 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)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• Repairing vulnerabilities without invisible hands. A differentiated replication study on LLMs [5.10123605644148]
  Automated Vulnerability Repair (AVR) is a fast-growing branch of program repair.<n>Recent studies show that large language models (LLMs) outperform traditional techniques.
  arXiv  Detail & Related papers  (2025-07-28T16:39:16Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)

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.