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

arXiv: https://arxiv.org/abs/2606.03329 · HTML: https://mlsanity.com/paper/2606.03329/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 26 of 26)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning](https://mlsanity.com/paper/2506.02867/) (2025)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents](https://mlsanity.com/paper/2509.23040/) (2025)
- [ERNIE-Doc: A Retrospective Long-Document Modeling Transformer](https://mlsanity.com/paper/2012.15688/) (2020)
- [QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management](https://mlsanity.com/paper/2512.12967/) (2025)
- [LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards](https://mlsanity.com/paper/2603.02146/) (2026)
- [LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards](https://mlsanity.com/paper/2602.05758/) (2026)
- [Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning](https://mlsanity.com/paper/2601.10306/) (2026)
- [CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning](https://mlsanity.com/paper/2601.14952/) (2026)

## Built on by (most cited first, 1 of 1)

- [CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory](https://mlsanity.com/paper/2609.36935/) (2026)

## Abstract (arXiv)

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.