The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces OPSD, a method that uses on‑policy self‑distillation to train a context‑free student model from a teacher conditioned on user memory, combined with a verify‑then‑regenerate router that directs queries to either weight or text memory. OPSD enables weight memory to compete with or surpass traditional text‑based memory systems on the HaluMem benchmark, reducing token usage per query. The study also explores how different training recipes influence weight memory performance and offers guidance for integrating it with retrieval in persistent, multi‑session agent deployments.
ForecastCompass (FoCo) is an adaptive factor-based memory framework designed to enhance agentic forecasting. It structures forecasting experience using a hierarchical task taxonomy and maintains two memory components: factor memory for reusable predictive dimensions and reasoning memory for probability updating, uncertainty handling, and calibration. Through a verbalized memory-revision process guided by retrospective analyses, FoCo iteratively refines its knowledge, leading to improved probabilistic accuracy and calibration in experiments with GPT-5-mini and Gemini-2.5-Flash on Prophet Arena and FutureX.
arXiv:2606. 14571v1 Announce Type: new Abstract: A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
The paper introduces FABench, a scalable backtesting environment designed to evaluate forecasting agents. FABench automatically discovers events, generates questions, and resolves outcomes for any past forecast date, allowing continuous renewal beyond model training cutoffs. In initial tests, retrieval improves Brier scores across eight models, with top agents matching or surpassing market consensus on 54 Polymarket-linked questions, yet analysis shows persistent evidence‑weighting failures that highlight room for improvement.
The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.