DISCERN: Preserve at Write, Resolve at Read for Persistent LLM-Agent Memory

Chirag Ahuja, Vladislav Tanov, Ramcharan Kakarla, Jonathan TawsarXiv 2026 · arXiv

This paper introduces DISCERN (DISambiguation and Cross-session Episodic memoRy Navigation), a framework that reimagines how LLM agents handle long-term, persistent memory. Rather than treating memory as a retrieval problem, the authors argue that the real challenge lies in resolution: correctly identifying entities, handling superseded facts, and knowing when to stay silent.

TL;DR

DISCERN moves agent memory from "retrieval-centric" to "resolution-centric" by following a simple rule: preserve at write, resolve at read. By maintaining a strictly additive, bi-temporal provenance graph and using an agentic navigation policy, it significantly outperforms existing systems in entity disambiguation and calibrated abstention.

What Problem Does This Paper Address?

In enterprise settings, agents accumulate memory over dozens of sessions. This leads to three major issues:

  1. Supersession: Facts change over time (e.g., a deal stage moves from "Negotiation" to "Closed Won").
  2. Entity Collision: Similarly named entities (e.g., "Zephyron Cloud Solutions" vs. "Zephyron Cloud Systems") blur together in vector space.
  3. The "Commitment" Problem: Standard RAG systems often hallucinate or blend facts because they lack a formal mechanism to decide if they have enough evidence to answer, or if they should clarify or abstain.

The authors demonstrate that for modern LLMs, retrieval (finding the right information) is largely solved, with baselines hitting 93-98% recall. The bottleneck is resolution—interpreting that retrieved data correctly.

Methods

DISCERN splits the memory process into two distinct paths:

1. Preserve at Write (The Store)

Instead of merging similar entities or overwriting old facts, DISCERN builds a strictly additive bi-temporal provenance graph.

  • Never Merge: Confusable entities are linked via SIMILAR_NAME edges but kept as distinct nodes.
  • Soft Invalidation: When a value changes, the old value is marked as "superseded" but retained. This allows the agent to answer questions about historical states (e.g., "What was the revenue before the acquisition?").

2. Resolve at Read (The Policy)

At query time, DISCERN doesn't just do a similarity search. It uses an agentic loop to navigate the graph using a suite of deterministic, zero-LLM tools (like find_similar_entities and check_temporal).

Figure 1: DISCERN end to end. Left: the per-actor event log is the immutable, append-only source of truth. Center (write time preserves): background consolidation materializes rebuildable derived views over the log, an entity-family graph that links confusable entities without merging them, a bitemporal fact store that soft-invalidates superseded values, and an episodic/profile layer; the cards show real benchmark cases (supersession, entity resolution, contamination isolation). Right (read time resolves): an adaptive policy navigates the views with a small read-only tool surface and commits one of four governed actions (answer, update, clarify, abstain) under the EarnedAnswerGate and EarnedAbstainGate, the DeclineRouter, and the near-miss guard.

The process culminates in one of four governed terminal actions:

  • ANSWER: A confident, cited response.
  • UPDATE: Returning the latest value in a chain of changes.
  • CLARIFY: Triggered when the agent finds "confusable twins" and needs more detail.
  • ABSTAIN: A verified refusal when information is missing.

Datasets

The authors evaluate DISCERN on two primary benchmarks:

  • ENT-310 (New): A synthetic enterprise sales-agent benchmark featuring 310 queries designed to test retention, currency, contamination (leaking facts between similar entities), and entity resolution. It includes 100 unanswerable "trap" questions to test abstention.
  • LoCoMo: An existing public benchmark of long-term personal conversations, used here to test out-of-domain generalization.

Key Insights and Ideas

  • Resolution > Retrieval: The "aha moment" is that even when a RAG system retrieves the correct passage, it often fails to resolve which specific entity or time-state the user is asking about.
  • Lossless Writing is Safer: Write-time merging is irreversible. By deferring the decision to merge or overwrite until read-time, the system remains flexible and avoids permanent data corruption.
  • Graph-Decidable Commitment: By using a labeled graph, the decision to answer or abstain becomes a decidable function of the graph structure (e.g., "If I find two viable candidates, I must CLARIFY") rather than a fuzzy LLM judgment.
Figure 2: The DISCERN memory graph showing how changed values are kept as bi-temporal edges and confusable entities are linked but never merged.

Key Results

  • Entity Resolution: On ENT-310, DISCERN achieved a score of 0.800, while no other baseline (including GraphRAG and HippoRAG2) exceeded 0.40.
  • Calibrated Abstention: DISCERN is the best-calibrated system for knowing when not to answer, achieving an F1 of 0.924 on unanswerable questions (compared to 0.802 for the best baseline).
  • Generalization: On the LoCoMo dataset, DISCERN led in macro answer correctness (0.663 vs 0.638) without any domain-specific tuning.

Limitations and Future Work

  • Latency: The agentic navigation loop is thorough but slow, averaging 4.1 turns and 5.7 tool calls per query (mean latency of 7.6s).
  • Backbone Sensitivity: The system relies heavily on the LLM's ability to follow complex tool-use instructions. Performance dropped significantly when using weaker open-weight models compared to Claude 3.5 Sonnet.
  • Future Work: The authors suggest training a specialized, smaller model to handle the navigation policy to reduce latency and cost.
Figure 3: The read-time routing procedure, illustrating the phases of orientation, ambiguity checks, and evidence gathering.

Summary updated

Abstract

Enterprise agents accumulate memory across dozens of sessions in which facts contradict, get superseded, and blur as similarly named entities collide in embedding space. The field treats this as a retrieval problem; we show it is not. On ENT-310, a synthetic enterprise sales-agent memory benchmark of 310 queries (210 answerable, 100 unanswerable), a vanilla Retrieval-Augmented Generation (RAG) reader over a memory store already matches strong memory systems on the recall pillars. Retention and currency are near-saturated, roughly 0.93 to 0.98 for every competent system, so recall is essentially solved. What remains unsolved is resolution: which entity a query refers to, which time-state is current, and whether to commit an answer at all or decline when evidence is insufficient. We propose DISCERN (DISambiguation and Cross-session Episodic memoRy Navigation), an agent-memory framework built on a single rule: preserve at write, resolve at read. At write time DISCERN builds a strictly additive bi-temporal provenance graph that never merges confusable entities and never drops superseded values. At read time a zero-LLM tool surface drives an agentic loop that navigates this graph and commits exactly one of four gated terminal actions. A four-judge LLM-as-a-Judge council scores two axes: answer correctness on answerable questions, and the answer-versus-abstain decision as a classification problem. On ENT-310, DISCERN is the best-calibrated system on abstention (F1 0.924 versus at most 0.802 across eight baselines) and leads macro answer correctness under equal pillar weighting (0.861 versus 0.806 for the strongest baseline), a lead driven by entity resolution (0.800, where no baseline exceeds 0.40). Applied with zero tuning to the full LoCoMo corpus, the same pipeline again leads macro answer correctness (0.663 versus 0.638) and stays among the best-calibrated on false-premise abstention.
BibTeX
@misc{ahuja2026discern,
  author = {Chirag Ahuja and Vladislav Tanov and Ramcharan Kakarla and Jonathan Taws},
  title = {{DISCERN: Preserve at Write, Resolve at Read for Persistent LLM-Agent Memory}},
  year = {2026},
  eprint = {2611.15729},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.15729},
}
Figure