AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorXiangchen Cheng →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorYunwei Jiang →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorJianwen Sun →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorZizhen Li →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorChuanhao Li →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorXiangcheng Cao →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorYihao Liu →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorFanrui Zhang →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorLi Jin →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- Linked via arxiv authorKaipeng Zhang →
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents