Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li +6 more

Published

Jul 2, 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

Jul 2, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics General Long Horizon

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.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, tool calls, and reflections to every prompt, which makes prior context easy to access but also turns it into a jumbled mixture in which the effect of any single memory component is hard to isolate. We introduce and instrument an alternative bounded contract: every decision is made from a fresh user message assembled by typed retrieval, with no raw cross-decision transcript appended. The prompt thus stays bounded across runs of any length, and any single layer can be ablated in isolation. We instantiate the contract in Slay the Spire 2, a closed-rule stochastic deck-building game whose runs require hundreds of tactical and strategic decisions. A public online benchmark of frontier LLMs on the same game reports zero wins at the lowest difficulty across five configurations, and the developer-reported human win rate at the same difficulty is 16%; the task is hard but not saturated. Within our harness, a fixed-A0 ablation shows the largest observed difference when triggered strategic skills are enabled: the no-store baseline wins 3/10 games and adding the skill layer 6/10. At this sample size the comparison is directional rather than statistically decisive (Fisher exact p\approx0.37); a cross-backbone probe and public accumulating-context baselines are reported as operational comparisons rather than controlled tests of the contract variable itself. We release a reproducible testbed: 298 completed trajectories with condition tags, frozen memory/skill snapshots, prompt records, and analysis scripts -- an agent design and a validated, reusable methodology for studying how explicit memory layers shape long-horizon LLM-agent decisions.

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.

"Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see."

Reported Metrics

partial

Win rate

Useful for evaluation criteria comparison.

"A public online benchmark of frontier LLMs on the same game reports zero wins at the lowest difficulty across five configurations, and the developer-reported human win rate at the same difficulty is 16%; the task is hard but not saturated."

Benchmarks and datasets

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

Reported metrics

win rate
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
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

Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.

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

Key takeaways

  • Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
  • The simplest contract appends past observations, tool calls, and reflections to every prompt, which makes prior context easy to access but also turns it into a jumbled mixture in which the effect of any single memory component is hard to isolate.
  • We introduce and instrument an alternative bounded contract: every decision is made from a fresh user message assembled by typed retrieval, with no raw cross-decision transcript appended.

Researcher actions

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

Win rate

Contribution summary

  • Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
  • We introduce and instrument an alternative bounded contract: every decision is made from a fresh user message assembled by typed retrieval, with no raw cross-decision transcript appended.
  • A public online benchmark of frontier LLMs on the same game reports zero wins at the lowest difficulty across five configurations, and the developer-reported human win rate at the same difficulty is 16%; the task is hard but not saturated.

Why it matters for eval

  • Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
  • A public online benchmark of frontier LLMs on the same game reports zero wins at the lowest difficulty across five configurations, and the developer-reported human win rate at the same difficulty is 16%; the task is hard but not saturated.

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: win rate