ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
Augmenting language models with long-term memory
12 Pith papers cite this work, alongside 33 external citations. Polarity classification is still indexing.
12
Pith papers citing it
33
external citations · external index
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Self-GC governs agent context as indexed objects with planner-proposed actions, achieving 84.85% no-impact on future continuations on a hard set versus 54-70% for baselines.
MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
LongRoPE extends LLM context windows to 2048k tokens via search for non-uniform positional interpolation, progressive fine-tuning from 256k, and short-context readjustment.
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
HYVE cuts LLM token usage on machine data by 50-90% using database-style hybrid views and a request-scoped datastore while maintaining or improving quality on tasks like anomaly detection and chart generation.
SUPERBROWSER reaches 89.47% success on Mind2Web Hard by implementing a human-like perception-cognition-action system with vision-first bounding boxes, a three-role brain, and an evicting ledger.
EMBER learns to retain budgeted, source-backed evidence capsules so long-horizon agents recover answer-relevant facts without rereading the full history.
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
The paper identifies inadequately addressed challenges in optimizing task allocation, fostering robust reasoning through debates, managing layered context, enhancing memory, and applying multi-agent systems to blockchain.
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
citing papers explorer
-
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
-
Self-GC: Self-Governing Context for Long-Horizon LLM Agents
Self-GC governs agent context as indexed objects with planner-proposed actions, achieving 84.85% no-impact on future continuations on a hard set versus 54-70% for baselines.
-
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
-
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
LongRoPE extends LLM context windows to 2048k tokens via search for non-uniform positional interpolation, progressive fine-tuning from 256k, and short-context readjustment.
-
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
-
HYVE: Hybrid Views for LLM Context Engineering over Machine Data
HYVE cuts LLM token usage on machine data by 50-90% using database-style hybrid views and a request-scoped datastore while maintaining or improving quality on tasks like anomaly detection and chart generation.
-
RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing Behaviour
SUPERBROWSER reaches 89.47% success on Mind2Web Hard by implementing a human-like perception-cognition-action system with vision-first bounding boxes, a three-role brain, and an evicting ledger.
-
EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
EMBER learns to retain budgeted, source-backed evidence capsules so long-horizon agents recover answer-relevant facts without rereading the full history.
-
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
-
LLM Multi-Agent Systems: Challenges and Open Problems
The paper identifies inadequately addressed challenges in optimizing task allocation, fostering robust reasoning through debates, managing layered context, enhancing memory, and applying multi-agent systems to blockchain.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
- MMLA: How Memory Lets the Past Shape the Future