arXiv Computation and Language November 4, 2026 By Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui, Lok Kan Chan, Ginny Y. Wong, Simon See

TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue

Read the original on arXiv Computation and Language →

TrackMem is a per-speaker graph memory designed to handle evolving beliefs in long-horizon financial dialogue, tracking figures, perspectives, and speaker actions over time. It addresses limitations of existing memory systems that rely on similarity or recency, which often return outdated or irrelevant information in financial contexts. Evaluated on the FinLoCoMo benchmark of 15 investment conversations, TrackMem outperforms baselines, achieving 73.9% macro accuracy on the failure-mode split and significant gains on questions about revised figures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Oct 16

TEM: Temporal State Tracking Memory for Large Language Model Agents

The paper introduces Temporal State Tracking Memory (TEM), a training‑free framework that stores facts as versioned records linked to their sources and retrieves the relevant versions in source order, labeling historical records before passing them to the answer model. TEM incorporates event memory and original dialogue turns to fill gaps in structured facts. Evaluations on 420 questions from 600 sessions with 60 personas show high key‑entity hit rates (75.71–97.62%) and significant improvements when historical labels are added, while keeping evidence compact (94–118 tokens per answer).

By Pengfeng Song, Yunkai Zhuang, Liye Shi

llms rag agents

arXiv Machine Learning

Sep 23

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

arXiv:2609.26780v1 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distingu...

By Haobo Zheng, Tan Tang, Yan Chen, Weijie Wang, Yingcai Wu

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 6

FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents

arXiv:2608. 04095v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons.

By Ben Wang, Kang Zhou, Lifan Guo, Feng Chen, Chi Zhang

llms agents benchmarks

arXiv AI

Aug 5

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.

By Yuxin Liao, Le Wu, Min Hou, Hao Liu, Han Wu, Zishu Wang

llms agents nlp

Hugging Face Trending Papers

Aug 2

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time.

llms agents safety

arXiv AI

Sep 1

Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection

arXiv:2608.29066v1 Announce Type: cross Abstract: Stance detection is crucial for understanding the underlying attitude of an expression towards a target. Conversational stance detection is a more ch...

By Yifan Xiang, Bin Liang, Yuqi Huang, Ruifeng Xu, Kam-Fai Wong

llms benchmarks

One email a morning, machine-written

Related stories

TEM: Temporal State Tracking Memory for Large Language Model Agents

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents

LeanMem: Simple and Efficient Long-Term Memory for LLM Agents

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection