TrawMem organizes agent memory by task role
On LoCoMo and MemGallery, authors report macro-F1 gains of 2.23–3.14 points and fewer context tokens than compared memory systems.
Stories per day · 30 days
Relatedagent-memory2llm-agents2retrieval2credit-assignment1deepseek1hotpotqa1longmemeval1memcompile1multi-agent1qwen1skill-learning1
6 stories, newest first · one card per story
Stories tagged #locomo
GRSE credits multi-agent skills by contrasting repeated runs
On HotpotQA and LoCoMo it beat MASkills on most categories, with the largest gains on multi-hop questions.
From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory
MemCompile compiles query-conditioned evidence for long-term agent memory, reaching 80.52% judge accuracy on LoCoMo.
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Pre-registered tests show raw turns selected by Jev match extracted agent memory at far lower cost.
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
SpeakerMem-R1 stores speaker-labeled messages and structured states, reaching 62.33% on EverMemBench.
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Jev-Mem uses a fast System-One controller for agent memory, beating baselines on LoCoMo while cutting latency.