Causal Episodic Memory for Feedback-Driven Agent Repair

• URL: http://arxiv.org/abs/2608.05906v1
• Date: Thu, 06 Aug 2026 11:34:03 GMT
• Title: Causal Episodic Memory for Feedback-Driven Agent Repair
• Abstract summary: We introduce MERIT, a training-free agent that maintains an online dual-polarity memory of oracle-verified corrections.<n>We show that negative memory contributes modestly, the value of type conditioning and lexical--dense ranking is dataset dependent, and schema-local experience provides the most consistent benefit.
• Score: 2.641347237473854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized repair outcomes can improve subsequent Text-to-SQL episodes without parameter updates. We introduce MERIT, a training-free agent that maintains an online dual-polarity memory of oracle-verified corrections and observed unsuccessful directions. Under oracle-assisted benchmark feedback, only memories from earlier finalized episodes are eligible for retrieval. A deterministic classifier assigns a coarse failure type, which conditions a hybrid lexical-dense retriever before the frozen model generates each revision. Using Qwen2.5-7B-Instruct with identical initial predictions and repair budgets, MERIT improves execution accuracy over stateless iterative repair from \(66.34\%\) to \(69.79\%\) on Spider and from \(47.35\%\) to \(48.44\%\) on BIRD. Paired analyses provide clear evidence for the Spider gain but weaker evidence on BIRD. MERIT is not reliably separated from untyped dynamic retrieval on either benchmark, while Reflexion-style memory reaches \(51.24\%\) on BIRD at substantially higher inference cost. Ablations show that negative memory contributes modestly, the value of type conditioning and lexical--dense ranking is dataset dependent, and schema-local experience provides the most consistent benefit. These results clarify when causal cross-query memory improves repair and when broader memory representations remain preferable.

Related papers

• Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability [2.8890052855500143]
  We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW)<n>We use 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters.
  arXiv  Detail & Related papers  (2026-09-04T16:44:17Z)
• Continual Graph Memory for Adaptive Recommendation under Intent Drift [7.140905344515738]
  This paper studies adaptive recommendation under intent drift, where feedback from each recommendation outcome can reveal whether the relational evidence used for ranking is useful, missing, or misleading.<n>This paper proposes CGM-Rec, a continual graph memory framework for adaptive recommendation.
  arXiv  Detail & Related papers  (2026-09-04T02:32:20Z)
• The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory [29.20695058395373]
  We introduce EARM, an experience-amortized reranking framework that treats previously acquired relevance scores as reusable retrieval experience.<n>EARM stores sparse query--memory relevance scores in an online matrix, learns their shared structure through causal matrix completion, and combines a small set of newly observed scores with estimated scores to rerank the remaining candidates.<n>Experiments on long-term conversational memory show that mixed observed-and-estimated reranking improves answer accuracy over semantic retrieval by up to 6.62%.
  arXiv  Detail & Related papers  (2026-08-24T03:42:03Z)
• From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents [19.125716338799545]
  textbfdependency-guided rollback repair builds a typed memory-to-action graph from provenance, traces explicit downstream dependencies, and selectively replays only answer-relevant affected computation.<n>We evaluate this approach on a 150-case controlled benchmark spanning three tool-use domains and four memory failure types.
  arXiv  Detail & Related papers  (2026-08-11T05:19:55Z)
• Contrastive Reflection for Iterative Prompt Optimization [0.6533652962118279]
  We present Contrastive Reflection, an iterative prompt-optimization framework for agentic IR.<n>We instantiate the framework with a tree-based slice selector, but the contribution is the contrastive loop rather than the tree itself.
  arXiv  Detail & Related papers  (2026-06-29T19:16:07Z)
• MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery [58.64329475683699]
  We argue that long-term memory should be evaluated as an auditable post-interaction artifact.<n>We instantiate this view in MEMPROBE, a benchmark in which a memory-equipped agent assists simulated users.<n>We find that successful assistance and recoverable memory behave as distinct capabilities.
  arXiv  Detail & Related papers  (2026-06-23T13:52:46Z)
• STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery [6.0574120466674986]
  LLM-based equation discovery offers a promising route to recovering symbolic laws from data.<n>We propose STRIDE, a self-reflective agent framework that improves reliability by coordinating data-aware generation, mixed-fitting evaluation, critic-executor repair, and diversity-preserving semantic memory.
  arXiv  Detail & Related papers  (2026-05-18T03:14:32Z)
• MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval [37.54115468116941]
  This report introduces MemReranker, a reranking model family (0.6B/4B) built on Qwen3-Reranker through multi-stage LLM knowledge distillation.<n>On the memory retrieval benchmark, MemReranker-0.6B substantially outperforms BGE-Reranker and matches open-source 4B/8B models as well as GPT-4o-mini on key metrics.<n>MemReranker-4B further achieves 0.737 MAP, with several metrics on par with Gemini-3-Flash, while maintaining inference latency at only 10-20% of large models.
  arXiv  Detail & Related papers  (2026-05-07T12:33:57Z)
• A Parametric Memory Head for Continual Generative Retrieval [52.66674234249913]
  Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries.<n>We show that sequential adaptation improves retrieval on newly added documents but substantially degrades performance on earlier slices.<n>We propose post-adaptation memory tuning (PAMT), a memory-only stabilization stage that augments an adapted model with a modular parametric memory head.
  arXiv  Detail & Related papers  (2026-04-25T17:38:51Z)
• Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction [2.6365690297272617]
  The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks.<n>We propose a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous claims.<n>We further introduce M$$C$+$, an ensemble-based framework that combines corrections across multiple rankers to reduce retrieval bias and improve robustness.
  arXiv  Detail & Related papers  (2026-04-21T14:13:07Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• ReFIT: Relevance Feedback from a Reranker during Inference [109.33278799999582]
  Retrieve-and-rerank is a prevalent framework in neural information retrieval. We propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time.
  arXiv  Detail & Related papers  (2023-05-19T15:30:33Z)

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.