[2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Core contribution

[2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents frames "[2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents" as research in the LLMs category. The central contribution should be read through the attached source evidence rather than as an announcement: what matters is the paper, benchmark, system design, or evaluation claim that can be inspected and reproduced.

Technical approach

[2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Skip to main content arXiv is now an independent nonprofit! Learn more× # Computer Science > Artificial Intelligence arXiv:2607.02255v1 (cs) [Submitted on 2 Jul 2026] # Title:AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Authors: Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang > 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...

For research in the LLMs category, the review should specifically look for model family, architecture or training clue, context length, benchmark deltas, deployment or inference constraints.

Evaluation setup

• [2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Skip to main content arXiv is now an independent nonprofit!
• Learn more× # Computer Science > Artificial Intelligence arXiv:2607.02255v1 (cs) [Submitted on 2 Jul 2026] # Title:AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Authors: Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng...
• [2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Skip to main content arXiv is now an independent nonprofit!
• Learn more× # Computer Science > Artificial Intelligence arXiv:2607.02255v1 (cs) [Submitted on 2 Jul 2026] # Title:AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Authors: Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang > 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 instantiate the contract in Slay the Spire 2, a closed-rule stochastic deck-building game whose runs require hundreds of tactical and strategic decisions.

Results and metrics

The strongest quantitative or technical signals found in the supplied excerpts are listed above. Treat them as source claims until the canonical paper, project page, or code release is checked directly.

Reproducibility notes

At least one attached source appears to be a code, model, or benchmark repository. Confirm license, setup instructions, evaluation scripts, and whether the reported results can be reproduced from the public artifacts.

Limitations and caveats

This dossier should separate what the authors or source documents claim from what can be independently inferred. If the sources omit baseline selection, benchmark construction, failure cases, or deployment constraints, those omissions should remain visible in the public research page.

Why this matters for AI builders

For builders tracking llms work, the useful question is whether this changes what to test, how to evaluate systems, or which assumptions to revisit. The candidate should help readers decide whether to inspect the paper/project more deeply, not just understand that it exists.

Source trail

• [2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents: https://arxiv.org/abs/2607.02255v1 - [2607.02255v1] AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Skip to main content arXiv is now an independent nonprofit! Learn more× # Computer Science > Artificial Intelligence arXiv:2607.02255v1 (cs) [Submitted on 2 Jul 2026] # Title:Ag...
• AgenticSTS — A Bounded-Memory Testbed for Long-Horizon LLM Agents: https://alayalab.github.io/AgenticSTS/ - AgenticSTS — A Bounded-Memory Testbed for Long-Horizon LLM Agents The problem (unbounded transcript memory), the bounded contract, why Slay the Spire 2 is a long-horizon testbed, and what the release provides. Unedited gameplay ## Watch it play The agent dr...
• AlayaLab/AgenticSTS-trajectories · Datasets at Hugging Face: https://huggingface.co/datasets/AlayaLab/AgenticSTS-trajectories - AlayaLab/AgenticSTS-trajectories · Datasets at Hugging Face License (mixed — read before reuse). Our trajectories (trajectories/,runs_history.jsonl) and analysis are CC-BY-4.0. Thecompetitors/*.tar.gz embed each competitor's own strategy/prompt docume...