Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Forget Freely, Grep Later: Lossless, Index-Free Memory for Long-Horizon LLM Agents

Ziyan Yang, Taiwei Shi, Jieyu Zhao

Published

Nov 18, 2026

Citations

0

Trust level

Low

Usefulness score

25/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 18, 2026

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

Abstract

Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later. Existing context management strategies rely on summarization, masking, or structured memory, requiring decisions about what to preserve or how to retrieve it before future needs are known. However, these methods can introduce lossy compression, potentially discarding details needed for future tasks. To address this limitation, we introduce GrepMem, a simple, lossless, and index-free memory mechanism built on two components: an append-only plain-text log of the agent's complete history and a regular-expression search tool for on-demand recall. Unlike structured memory systems, GrepMem requires no embeddings, retrieval index, memory extraction, or additional models. We train Qwen3.5-9B with reinforcement learning under five context management strategies and evaluate on multi-question research sessions, long-stream recall, and agent-trajectory question answering. GrepMem achieves 95-97% accuracy on ContextBench, versus at most 21% for lossy baselines, and outperforms SUPO's summarization by 8.8 percentage points on BCP-Multi. GrepMem scales effectively to increasingly long input streams while remaining on the accuracy-token-cost Pareto frontier across all five evaluation tasks. Our results show that a plain-text log and grep provide a simple but competitive approach to long-horizon agent memory, without requiring complex structured memory infrastructure.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"GrepMem achieves 95-97% accuracy on ContextBench, versus at most 21% for lossy baselines, and outperforms SUPO's summarization by 8.8 percentage points on BCP-Multi."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Trajectory (inferred)
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later.
  • Existing context management strategies rely on summarization, masking, or structured memory, requiring decisions about what to preserve or how to retrieve it before future needs are known.
  • However, these methods can introduce lossy compression, potentially discarding details needed for future tasks.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics, Long-horizon tasks) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later.
  • Existing context management strategies rely on summarization, masking, or structured memory, requiring decisions about what to preserve or how to retrieve it before future needs are known.

Why it matters for eval

  • We train Qwen3.5-9B with reinforcement learning under five context management strategies and evaluate on multi-question research sessions, long-stream recall, and agent-trajectory question answering.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy