TIDER：用强化学习定位时间窗口，改进 LLM 智能体长期记忆检索
RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
记忆检索总被时间对不上的相似内容干扰？这篇提出 TIDER，用 1.7B 小模型+RL 定位时间窗口再检索，LifeBench 和 LoCoMo 两个基准都刷新了纪录。
论文提出 TIDER，一个时间感知的智能体检索框架。核心是一个用强化学习训练的 1.7B 时间区间定位器，在检索阶段先推断证据所在的时间窗口，再将时间通道与语义通道结果合并重排，解决语义相似但时间错位的记忆挤掉目标证据的问题。在 LifeBench 上达到 61.52%（提升 8.82%），在 LoCoMo 上达到 78.96%（提升 3.66%），两项均为当前最优成绩。方法借鉴人类情景记忆中的时间邻近效应，用组合奖励把稀疏的答案监督转化为细粒度检索反馈。
RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
Time-aware retrieval is crucial for long-horizon LLM agents to effectively leverage ever-growing long-term memory. Existing methods focus on lexical or semantic similarity, leading to target memories being crowded out by temporally mismatched yet semantically similar candidates. Even time-aware approaches inject temporal cues only during memory organization or answer generation, overlooking temporal constraints at the retrieval stage, where candidate selection occurs - the root cause of the displacement. Inspired by the temporal contiguity effect in human episodic memory, we propose TIDER (Temporal Interval-driven Dual-channel Evidence Retrieval), a time-aware agentic retrieval framework. Central to TIDER is a reinforcement learning (RL)-trained temporal interval locator that infers the temporal windows in which the evidence lies. RL optimizes window localization as a discrete, non-differentiable retrieval decision, using composite rewards to convert sparse answer supervision into fine-grained retrieval feedback. These temporal windows first define the temporal retrieval channel; the retrieved candidates are then merged with results from the semantic channel and reranked by proximity to the windows. This temporal grounding enables TIDER to retrieve temporally aligned evidence that would otherwise be drowned out by the volume of semantically similar yet temporally mismatched memories. With a lightweight 1.7B locator, TIDER achieves state-of-the-art accuracy on both long-horizon memory benchmarks - 61.52% on LifeBench (+8.82%) and 78.96% on LoCoMo (+3.66%) - which indicates that temporal cues are crucial for pinpointing target evidence amid a vast pool of semantically similar historical events in long-term daily-life memory.