MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
hub Canonical reference
Memorybank: Enhancing large language models with long-term memory
Canonical reference. 80% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
years
2026 11representative citing papers
Proposes a claim-calibrated evidence ladder and evaluation protocol with explicit-memory baselines to assess whether TTT produces deployment-usable behavioral memory rather than just proxy metric gains.
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.
Geometry-aware FGW prior transfer plus PAC-Bayes residual adaptation reduces topology forgetting and raises average accuracy across continual multi-agent topology learning streams.
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
Auto-Dreamer trains an offline memory consolidator via GRPO on agent performance to abstract cross-session patterns, outperforming baselines by 7 points on ScienceWorld with 12x smaller memory and generalizing to ALFWorld and WebArena.
A single long-horizon agent with dependency-aware traversal and RepoMemory produces more complete, consistent, hierarchical repository documentation than open and closed baselines.
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
Bian Que is an agentic framework using a unified operational paradigm, flexible Skill Arrangement, and self-evolving mechanism to automate O&M tasks, achieving 75% alert reduction and over 50% MTTR cut in production deployment.
citing papers explorer
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
Proposes a claim-calibrated evidence ladder and evaluation protocol with explicit-memory baselines to assess whether TTT produces deployment-usable behavioral memory rather than just proxy metric gains.
-
MemGym: a Long-Horizon Memory Environment for LLM Agents
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.
-
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
Geometry-aware FGW prior transfer plus PAC-Bayes residual adaptation reduces topology forgetting and raises average accuracy across continual multi-agent topology learning streams.
-
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
Self-Evolving Multi-Agent Systems via Decentralized Memory
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
-
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
Auto-Dreamer trains an offline memory consolidator via GRPO on agent performance to abstract cross-session patterns, outperforming baselines by 7 points on ScienceWorld with 12x smaller memory and generalizing to ALFWorld and WebArena.
-
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
A single long-horizon agent with dependency-aware traversal and RepoMemory produces more complete, consistent, hierarchical repository documentation than open and closed baselines.
-
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
-
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
Bian Que is an agentic framework using a unified operational paradigm, flexible Skill Arrangement, and self-evolving mechanism to automate O&M tasks, achieving 75% alert reduction and over 50% MTTR cut in production deployment.