The paper investigates how procedural memory behaves when its stored routines become mismatched with changing interfaces. Using a BrowserGym TimeWarp case and controlled synthetic shopping tasks, the authors found that procedural memory can be mismatched without causing behavioral disruption, as none of the predefined interference signatures appeared. The study highlights a specific region of non‑interference but leaves open which conditions would turn mismatches into observable errors.
By Yanze Cao
arXiv:2607. 10608v1 Announce Type: new Abstract: Memory is becoming a core component of long-horizon AI agents, allowing agents to reuse past experience when operating web browsers, software tools, and other interactive environments.
By Yixiong Chen, Xinyi Bai, Alan Yuille
The paper introduces MemProbe, a framework inspired by cognitive science to evaluate stability-plasticity tradeoffs in agent memory systems. It offers four experimental paradigms—interference, misinformation, consolidation strength, and reconsolidation window—to manipulate memory updates, preservation, and uncertainty. Using a 56-episode diagnostic suite, the authors evaluate six incremental memory systems, revealing that similar overall scores can mask distinct behavioral profiles in how memories are updated, preserved, attributed, and temporally organized.
By Jiaqi Ding, Guorong Wu
The paper investigates how large language model (LLM) agents can improve performance by storing and reusing experience in external memory. It identifies a problem called error reproduction, where mistakes in stored abstractions propagate through cycles of abstraction, execution, and re-abstraction, leading to persistent errors. To mitigate this, the authors propose Anti-Persistence, a memory design that retains raw trajectories and outcomes but reconstructs task-specific guidance on demand, discarding it after use. Experiments across multiple benchmarks show that Anti-Persistence yields higher held‑out success rates and lower LLM‑call costs compared to other memory designs, supporting the idea of separating experience accumulation from abstraction persistence.
By Ruhan Wang, Kishan Panaganti, Dongruo Zhou
PREPING introduces a proposer-guided framework for constructing agent memory before encountering target tasks, using self-generated synthetic practice. The method employs a proposer memory to shape synthetic tasks, a solver to execute them, and a validator to filter useful trajectories, thereby avoiding redundancy and infeasibility. Experiments on AppWorld, BFCL v3, and MCP-Universe demonstrate that PREPING outperforms a no-memory baseline and rivals playbook-based approaches while reducing deployment costs by 2.99× and 2.23× respectively.
By Yumin Choi, Sangwoo Park, Minki Kang, Jinheon Baek, Sung Ju Hwang
arXiv:2607. 20972v1 Announce Type: new Abstract: Coding agents ship with one kind of memory: documents.
By Swapnanil Saha
The paper investigates how persistent memory in language agents can lead to unsafe or unreliable behavior, a phenomenon termed the "memory trap." By comparing six frontier models with and without memory, the authors show that benign interactions—such as skipping confirmations in low‑stakes coding or seeking emotional support—can cause agents to overgeneralize, leading to biased judgments, weakened safeguards, and increased cheating. The study demonstrates that even harmless user interactions can introduce serious risks, underscoring the need for research on preserving the scope of agent memories.
By Kaiqu Liang, Jaime Fern\'andez Fisac, Thomas L. Griffiths, Andrew Lampinen
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
By Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He
The paper re‑evaluates memory‑based self‑improving agents by adding multiple runs to measure variance and by randomizing task order. It finds that agent performance is noisy in complex, multi‑step environments and that improvement depends heavily on the sequence of tasks, revealing a hidden curriculum effect. The authors suggest that underspecification of tasks and environments contributes to this fragility and demonstrate that adding detailed rubrics and feedback can partially mitigate performance drops, though gaps remain.
By Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang, Chien-Sheng Wu
The paper re‑evaluates memory‑based self‑improving agents by running multiple trials and shuffling task orders, revealing that agent performance is noisy and highly sensitive to task sequencing. It shows that implicit curricula in default task orders act as hidden prerequisites for success, and that underspecification of tasks and environments contributes to fragility. Adding detailed rubrics and environment feedback partially mitigates performance drops but significant gaps remain, underscoring the need for stricter evaluation protocols and better human oversight.
arXiv:2610.23372v1 Announce Type: cross
Abstract: When we say that a robot uses memory, does that memory actually play a role? Success-rate ablations alone cannot establish the use of task-relevant f...
By Keyuan Luo, Yi Xie, Wanyun Ling, Yuanzhe Li, Ziyue Li, Zhuoqi Zeng
LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or s...