memory-augmented-agents

Tag

Cards List
#memory-augmented-agents

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

arXiv cs.CL · 4d ago Cached

This paper presents a holistic evaluation of memory substrates for memory-augmented LLM agents, finding that no single substrate dominates across all regimes and advocating for adaptive substrate routing to optimize performance in different operating conditions.

0 favorites 0 likes
#memory-augmented-agents

From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents

arXiv cs.AI · 2026-08-12 Cached

This paper introduces dependency-guided rollback repair for memory-augmented agents, a method that builds a typed memory-to-action graph from runtime provenance to selectively undo faulty memory effects while preserving benign state, achieving strong recovery on benchmarks.

0 favorites 0 likes
#memory-augmented-agents

MemHarness: Memory Is Reconstructed, Not Replayed

Hugging Face Daily Papers · 2026-07-30 Cached

MemHarness is a framework that enables LLM agents to reconstruct past experiences conditioned on the current context instead of replaying them verbatim, improving performance on ALFWorld and WebShop while reducing negative transfer.

0 favorites 0 likes
#memory-augmented-agents

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

Hugging Face Daily Papers · 2026-05-14 Cached

MemLens is a new benchmark for evaluating memory capabilities in large vision-language models through multi-session conversations. It compares long-context and memory-augmented approaches, revealing limitations in both and motivating hybrid architectures.

0 favorites 0 likes
← Back to home

Submit Feedback