Research Papers Topics
How AI agents store, retrieve, and update long-term memory across tasks and sessions — beyond the context window.
Agent Memory · National University of Singapore
EvoArena turns static agent tasks into evolving chains and finds current agents average only 39.6% accuracy; EvoMem adds patch memory and improves chain-level accuracy by 3.7 points.
World Models · JD.com (Joy Future Academy)
When a camera revisits an old spot, block-wise state-space recurrence scored 69.0 open-domain VLM consistency vs 12.25 for the no-memory baseline; aggressive compression and spatial summaries mostly collapsed.
Multimodal Models · Peking University
A survey that reframes long-video MLLMs as three abilities (watch, remember, reason), comparing against 11 prior surveys and organizing 100+ methods plus 5 application domains.
AI Agents · Shanghai Jiao Tong University
A hypernetwork compiles a textual skill into a LoRA adapter in one forward pass. On ALFWorld, LatentSkill lifts success by 21.4 points (seen) with 64.1% fewer prefill tokens.
OpenSkill lets agents build skills and their own verifiers from the open web, hitting 43.6% on SkillsBench (+8.9 over the best baseline) with zero target-task answers.
SkillAdaptor edits an agent's skill library from failed trajectories without touching model weights, lifting WebShop score +2.3 and PinchBench +1.5 over the frozen backbone.
TaskMem trains a multimodal agent to write its own memory with RL, lifting streaming-video QA accuracy to 67.9% on VideoMME and 45.4% on EgoLife, gains of 6.3 and 7.0 points over the Qwen3-VL-30B baseline.
MemGPT borrows OS virtual memory — it lets the LLM page data in and out of its own context with function calls, lifting deep memory retrieval to 93.4% with GPT-4 vs 35.3% for recursive summarization.
Long Context · Shanghai AI Laboratory
δ-mem bolts a tiny 8×8 delta-rule memory onto a frozen LLM and lifts average long-memory scores 1.10× over the backbone and 1.15× over other memory methods — no fine-tuning, no context extension.
MemPrivacy swaps sensitive spans for type-aware placeholders on-device, processes memory in the cloud over them, then restores them locally — utility loss stays within 1.6% and 0.6B-4B models beat GPT-5.2 at detection.