Grounding Agent Memory in Contextual Intent

ACL ARR 2026 January Submission2407 Authors

Keywords: Agentic Memory, Context-Aware Retrieval, Long-Horizon Reasoning, Retrieval Cues, Large Language Model Agents

Abstract:

Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and con-straints, causing memory systems to retrieve context-mismatched evidence. We propose STITCH (Structured Intent Tracking in Contextual History), an agentic memory system that indexes each trajectory step with a structured retrieval cue, contextual intent, and retrieves history by matching the current step's intent. Contextual intent provides compact signals that disambiguate repeated mentions and reduce interference: (1) the current latent goal defining a thematic segment, (2) the action type, and (3) the salient entity types anchoring which attributes matter. During inference, STITCH filters and prioritizes memory snippets by intent compatibility, suppressing semantically similar but context-incompatible history.

For evaluation, we introduce CAME-Bench, a benchmark for context-aware retrieval in realistic, dynamic, goal-oriented trajectories. Across CAME-Bench and LongMemEval, STITCH achieves state-of-the-art performance, outperforming the strongest baseline by 35.6%, with the largest gains as trajectory length increases. Our analysis shows that intent indexing substantially reduces retrieval noise, supporting intent-aware memory for robust long-horizon reasoning.'

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Language Modeling, Dialogue and Interactive Systems, Information Retrieval and Text Mining, Resources and Evaluation

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 2407