# From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents arXiv: https://arxiv.org/abs/2608.10502 · HTML: https://mlsanity.com/paper/2608.10502/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. - Builds on 19 of its 28 references that are in the map. - First posted on arXiv 11 Aug 2026. ## Placed in - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) ## Builds on (most cited first, 19 of 19) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023) - [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024) - [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023) - [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023) - [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025) - [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024) - [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024) - [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025) - [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025) - [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025) - [AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications](https://mlsanity.com/paper/2602.22769/) (2026) - [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026) - [Memory Poisoning Attack and Defense on Memory Based LLM-Agents](https://mlsanity.com/paper/2601.05504/) (2026) - [LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues](https://mlsanity.com/paper/2605.12493/) (2026) - [Useful Memories Become Faulty When Continuously Updated by LLMs](https://mlsanity.com/paper/2605.12978/) (2026) - [MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents](https://mlsanity.com/paper/2505.20231/) (2025) - [MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection](https://mlsanity.com/paper/2605.23723/) (2026) ## Built on by (most cited first, 8 of 8) - [Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective](https://mlsanity.com/paper/2608.30563/) (2026) - [Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification](https://mlsanity.com/paper/2608.17247/) (2026) - [Noise Floor Audit for Agent Benchmarks](https://mlsanity.com/paper/2608.22331/) (2026) - [DIAG: Diagnostic Iterative Alignment and Generation for Data-Efficient Mathematical Preference Distillation](https://mlsanity.com/paper/2608.22806/) (2026) - [When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents](https://mlsanity.com/paper/2610.03902/) (2026) - [VitaBench: Memory Lifecycles Beyond Retrieval](https://mlsanity.com/paper/2610.14731/) (2026) - [Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations](https://mlsanity.com/paper/2610.15154/) (2026) - [What Breaks in Multi-Image Schema Application? Factorial Oracle Interventions Reveal an Instance-Information Bottleneck](https://mlsanity.com/paper/2610.19611/) (2026) ## Abstract (arXiv) Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes. Existing defenses mainly detect or delete suspicious memories, or revise the current response. Deleting the source leaves already propagated claims, actions, and derived memories active, whereas resetting the store or replaying the full trace destroys benign state and repeats unnecessary computation. We therefore formulate post-failure memory recovery: textitgiven a failed execution and diagnosed faulty memories, recover both the answer and persistent state while retaining unaffected work. Our dependency-guided rollback repair builds a typed memory-to-action graph from runtime provenance, traces explicit downstream dependencies, preserves candidates with independent trusted support, deactivates unsupported memory state, and selectively replays only answer-relevant affected computation. We evaluate this approach on a 150-case controlled benchmark spanning three tool-use domains and four memory failure types, and on a 50-case trajectory-derived stress test adapted from LongMemEval-V2. On the controlled benchmark, it achieves 85.3% recovery versus 77.3% for the best competing recovery method, removes all diagnosed faulty memories, preserves all benign memories, and requires only selective replay with modest LLM-call cost. On the adapted subset, it reaches 68.0% recovery versus 54.0% for the next best method, while also achieving the highest claim invalidation F1, 0.669 versus 0.603. Overall, the results do not imply uniformly better trace reconstruction, but show that dependency-guided rollback repair provides a strong recovery--cost trade-off while repairing faulty memory state and preserving benign memory.