Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916071877902336 |
|---|---|
| author | Lin, Jingjie Wang, Bingbing Wang, Zihan Jin, Zhengda Qiao, Weiming Li, Jing Xu, Ruifeng |
| author_facet | Lin, Jingjie Wang, Bingbing Wang, Zihan Jin, Zhengda Qiao, Weiming Li, Jing Xu, Ruifeng |
| contents | Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations. To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue. RefMem-Bench contains 26K annotated QA instances with eight reflective-memory dimensions and three task formats, requiring models to move beyond surface-level retrieval and infer latent meanings from evidence distributed across interaction histories. To enhance reflective memory capability, we propose REflective Memory INDuction (REMIND), a hierarchical framework that treats reflective memory as progressive meaning construction. REMIND couples question-conditioned evidence retrieval, salience-aware grounding, and abstraction-level supervision, and uses Progressive Reflective Alignment to distill high-level reflective reasoning into the factual inference pathway. Experiments show RefMem-Bench poses a substantial challenge to current models, while REMIND consistently improves both answer accuracy and memory recall through progressive evidence perception, grounding, and abstraction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01223 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue Lin, Jingjie Wang, Bingbing Wang, Zihan Jin, Zhengda Qiao, Weiming Li, Jing Xu, Ruifeng Computation and Language Artificial Intelligence Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into high-level interpretations. To address this gap, we introduce RefMem-Bench, a benchmark for reflective memory in long-horizon dialogue. RefMem-Bench contains 26K annotated QA instances with eight reflective-memory dimensions and three task formats, requiring models to move beyond surface-level retrieval and infer latent meanings from evidence distributed across interaction histories. To enhance reflective memory capability, we propose REflective Memory INDuction (REMIND), a hierarchical framework that treats reflective memory as progressive meaning construction. REMIND couples question-conditioned evidence retrieval, salience-aware grounding, and abstraction-level supervision, and uses Progressive Reflective Alignment to distill high-level reflective reasoning into the factual inference pathway. Experiments show RefMem-Bench poses a substantial challenge to current models, while REMIND consistently improves both answer accuracy and memory recall through progressive evidence perception, grounding, and abstraction. |
| title | Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2606.01223 |