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

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-07-04T03:50:58+00:00
Episode link: https://share.transistor.fm/s/f25d5edd
Audio file: https://media.transistor.fm/f25d5edd/71686616.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents
Duration seconds: 1410

## Resource

🤗 Upvotes: 41 | cs.AI, cs.CL Authors: Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang Title: AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Arxiv: http://arxiv.org/abs/2607.02255v1 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…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/agenticsts-a-bounded-memory-testbed-for-long-horizon-llm-agents.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.