AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

Yaorui Shi, Yuxin Chen, Siyuan Wang, Sihang Li, Hengxing Cai, Qi GU, Xiang Wang, An Zhang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 30 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add history-callback memory retrieval to RL-trained memory agent (ReMemR1 vs MemAgent)MemAgent (Qwen2.5-7B) · HotpotQA (6400 docs)accuracy: 75.8 -> 80.8Improved
add callback retrievalMemAgent (Qwen2.5-3B) · 2WikiMultiHopQA (50 docs)accuracy: 41.4 -> 53.5Improved
add callback retrievalMemAgent (Qwen2.5-3B) · HotpotQA (50 docs)accuracy: 70.3 -> 70.9Improved
add callback retrieval at short context without RLMemAgent (Qwen2.5-3B, no RL) · HotpotQA (50 docs)accuracy: 60.2 -> 35.4Hurt
add callback retrieval at long context without RLMemAgent (Qwen2.5-3B, no RL) · HotpotQA (6400 docs)accuracy: 14.1 -> 20.5Improved
use rule-based question-as-query callback instead of RL-learned callback (ablation)MemAgent (Qwen2.5-3B) · HotpotQA (400 docs)accuracy: 68.8 -> 60.9Hurt
use rule-based question-as-query callback (ablation)MemAgent (Qwen2.5-3B) · HotpotQA (6400 docs)accuracy: 58.8 -> 60.9Improved
use rule-based callback (ablation)MemAgent (Qwen2.5-3B) · 2WikiMultiHopQA (400 docs)accuracy: 41.4 -> 35.2Hurt
add step-level state rewards (alpha 1.0 -> 0.8) (ablation)ReMemR1 (Qwen2.5-3B) · HotpotQA (400 docs)accuracy: 59.6 -> 74.0Improved
lower alpha to 0.2 (overweight step-level reward) (ablation)ReMemR1 (Qwen2.5-3B) · HotpotQA (6400 docs)accuracy: 66.1 -> 52.0Hurt
add RL training (ablation)ReMemR1 (Qwen2.5-3B) · HotpotQA (6400 docs)accuracy: 20.5 -> 66.1Improved
alpha 1.0 vs 0.8 at 100 docs (ablation)ReMemR1 (Qwen2.5-3B) · HotpotQA (100 docs)accuracy: 73.4 -> 71.7Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy