Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain

About

Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by sequentially reading document chunks, updating a compact memory, and generating the final answer from the accumulated memory. However, existing RL-based chunk-wise agents either rely on sparse final-answer rewards or use lexical intermediate rewards for memory and retrieval actions. These signals supervise task success or local overlap, but do not directly evaluate whether the final memory supports the ground-truth answer. We propose InfoMem, a reward mechanism for training chunk-wise memory agents that evaluates final-memory utility using answer-conditioned information. InfoMem measures how much the final memory increases the model's per-token log-likelihood of the ground-truth answer. To stabilize RL optimization, InfoMem applies this signal only to successful trajectories and normalizes it before reward composition. Under the same GRPO framework and training budget, InfoMem improves long-context memory-agent performance over comparable memory-agent RL baselines. Analyses show that effective final-memory rewards should operate on successful trajectories, be normalized before reward composition, and be conditioned on the answer rather than the query. Our code is available at https://github.com/GenSouKa1/InfoMem.

Tiancheng Han, Yong Li, Wuzhou Yu, Qiaosheng Zhang, Wenqi Shao• 2026

Related benchmarks

TaskDatasetResultRank
Corpus-level evidence aggregationCorpusQA 128K-token
LLM-as-Judge Accuracy19.453
4
Long-horizon dialogue memory and conversational information trackingLongMemEval 115K-token S
LLM-as-Judge Accuracy12.8
4
Multi-needle retrievalMRCR-8needle 100-example
Sequence Match Accuracy27.9
4
Sparse retrieval-style question answeringRULER synthetic QA (standard)
F1 Score0.3685
4
Showing 4 of 4 rows

Other info

Follow for update