The paper introduces WikiTrace, an evidence‑linked memory system for large language model agents that stores lessons alongside the original trajectories that produced them. By allowing agents to verify and refine lessons against their source data, WikiTrace reduces memory‑induced degradation—situations where agents fail tasks due to incorrect or misapplied lessons. Experiments on five agentic benchmarks show that WikiTrace consistently outperforms existing memory approaches and a baseline using the same insights alone.
By Yukyeong Lee, Yumin Choi, Jinheon Baek, Sung Ju Hwang
The paper introduces WikiTrace, an evidence‑linked memory system for large language model agents. WikiTrace stores each lesson as a concise insight tied to a summary of its success or failure and the raw trajectory that produced it, allowing agents to verify and correct lessons before applying them. Experiments on five agentic benchmarks show that WikiTrace outperforms existing memory approaches and reduces memory‑induced degradation.
Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators. However, memory is not always beneficial: retrieved memories often induce a critical issue of sycophancy, causing agents to over-align with the user at the cost of factual accuracy or objective reasoning.
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
arXiv:2607. 01071v1 Announce Type: cross Abstract: Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators.
By Zhishang Xiang, Zerui Chen, Yunbo Tang, Zhimin Wei, Ruqin Ning, Yujie Lin, Qinggang Zhang, Jinsong Su
The paper introduces FAME, a training‑free framework that evaluates false memory in autonomous agents by tracking how their internal beliefs shift under counterfactual scenarios. False memory, defined as biases arising from spurious correlations, environment shifts, or knowledge conflicts, is hard to detect with standard methods. FAME measures concept drift in hidden states, achieving AUROCs between 76.2% and 96.7% and outperforming baselines on benchmarks such as GSM‑Symbolic, GitChameleon, and BigBench‑Hard.
By Quan M. Tran, Zhuo Huang, Zhen Fang, Jing Zhang, Mingming Gong, Tongliang Liu
Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading only the agent's observable behavior are barely better than chance.
arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.
By Bingrui Sima, Lizhong Wang, Xiaoya Lu, Kun He, Xiao Yang
arXiv:2606.31422v3 Announce Type: replace
Abstract: Long-horizon language agents enable autonomous decision-making in complex environments by planning and executing sequences of interdependent action...
By Xinyuan Song, Zekun Cai
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
arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.
By Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States introduces PoS, an inference-time framework that builds and maintains explicit belief states to guide large language model agents. Each belief state combines an estimate of the current world with unresolved task requirements, making clear what the agent still needs to learn and accomplish. PoS validates consistency, monitors task progress to detect Belief Trapping, and tailors recovery to the trapping pattern and unresolved requirements, achieving top performance across four benchmarks with all three LLM backbones.
By Yu Luo, Jiamin Jiang, Yimin Zuo, Xidao Wen, Rongchen Gao, Yongqian Sun, Shenglin Zhang, Guiyang Liu, Cheng Zhang, Fang Situ, Qi Zhou, Dan Pei