MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
hub
A human- inspired reading agent with gist memory of very long contexts
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
SCG-MEM reformulates agent memory access as schema-constrained generation within dynamic cognitive schemas, using assimilation and accommodation for updates plus an associative graph for reasoning, and outperforms retrieval baselines on the LoCoMo benchmark.
HiGMem combines hierarchical event-turn memory with LLM-guided selection to retrieve concise relevant evidence from long dialogues, improving F1 scores and cutting retrieved turns by an order of magnitude on the LoCoMo10 benchmark.
GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
MiA-Signature approximates the global activation state induced by a query via submodular concept selection to enable tractable long-context understanding in LLMs.
EngramaBench shows structured graph memory outperforms full-context prompting on cross-space reasoning in long conversations but scores lower overall than full-context and higher than vector retrieval.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.