Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

How Much Should an Agent Remember? Deployment Lessons from Self-Distilled Memory for LLM Agents

K. R. Jayaram, Vatche Isahagian, Aswath Vaithinathan Aravindan, Vinod Muthusamy +5 more

Published

Nov 19, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

15% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 19, 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

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

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

Abstract

LLM agents on long-horizon tasks fail in recurring, procedural ways. They mis-paginate an API, resolve the wrong entity, or answer when no answer was asked. We built a pipeline that lets an agent learn from its own history. It first mines short \emph{lessons} from the agent's own trajectories, one to three per episode. It then consolidates those lessons into a smaller set of \emph{guidelines}, where each guideline records how many lessons it merged. At inference the agent receives either all guidelines or a selected subset. The pipeline ships in the open-source altk-evolve library and is deployed in IBM's CUGA agent and watsonx Orchestrate platform. We report what we learned building, measuring, and productizing it. Our primary instrument is the AppWorld benchmark, across models spanning 40--92\% baseline task completion. The central finding is that the right amount of memory is a property of the model, not the memory. A strong model keeps improving as guidelines are added. DeepSeek-V3.2 gains +9.5 points of task completion and +16.1 points of scenario completion with its full 191-guideline set. A weak model gains less from the same full set than from a small selected subset. gpt-oss-120b starts at 39.9\% task completion. It reaches 51.2\% with all 199 of its guidelines but 55.4\% (mean of two runs) with a selected subset of about 29. Around that result we report what went wrong: a high-support guideline that backfired, provenance silently dropped during consolidation, a swallowed API error that failed every task while producing a plausible log, and a baseline confound that nearly produced a misleading comparison with a prior method. We distill these into recommendations for teams deploying agent memory.

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.

"LLM agents on long-horizon tasks fail in recurring, procedural ways."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"LLM agents on long-horizon tasks fail in recurring, procedural ways."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLM agents on long-horizon tasks fail in recurring, procedural ways."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"LLM agents on long-horizon tasks fail in recurring, procedural ways."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"LLM agents on long-horizon tasks fail in recurring, procedural ways."

Benchmarks and datasets

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

Reported metrics

No metric terms were extracted from the available abstract.

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
None
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

LLM agents on long-horizon tasks fail in recurring, procedural ways.

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

Key takeaways

  • LLM agents on long-horizon tasks fail in recurring, procedural ways.
  • They mis-paginate an API, resolve the wrong entity, or answer when no answer was asked.
  • We built a pipeline that lets an agent learn from its own history.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Tool-use evaluation, 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

  • LLM agents on long-horizon tasks fail in recurring, procedural ways.
  • They mis-paginate an API, resolve the wrong entity, or answer when no answer was asked.

Why it matters for eval

  • Our primary instrument is the AppWorld benchmark, across models spanning 40--92\% baseline task completion.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • 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

    No metric terms extracted.