LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
Look back to reason forward: Revis- itable memory for long-context llm agents.arXiv preprint arXiv:2509.23040, 2025a
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
years
2026 12representative citing papers
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
SAM is a standalone memory framework for long-horizon LLM agents that creates state-adaptive cues from interactions, preserves raw trajectories for intent-driven recall, and optimizes the module via expert supervision and RL, outperforming baselines on BrowseComp and related benchmarks.
MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.
ActiveMem proposes a heterogeneous distributed memory framework for LLM agents that separates planning from active memory management, reporting SOTA accuracy with lower overhead on BrowseComp-Plus and GAIA.
NoisyAgent trains LLM agents with controlled user and tool noise to improve robustness in stochastic environments while also boosting clean-benchmark performance.
MiA-Signature approximates the global activation state induced by a query via submodular concept selection to enable tractable long-context understanding in LLMs.
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
MICA mixes per-turn and whole-trajectory normalized reward signals to train emotional-support chatbots, outperforming GRPO and REINFORCE++ on EMPA, EQ-Bench, and EmoBench.
MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.
MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.
citing papers explorer
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
-
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
SAM is a standalone memory framework for long-horizon LLM agents that creates state-adaptive cues from interactions, preserves raw trajectories for intent-driven recall, and optimizes the module via expert supervision and RL, outperforming baselines on BrowseComp and related benchmarks.
-
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.
-
ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
ActiveMem proposes a heterogeneous distributed memory framework for LLM agents that separates planning from active memory management, reporting SOTA accuracy with lower overhead on BrowseComp-Plus and GAIA.
-
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
NoisyAgent trains LLM agents with controlled user and tool noise to improve robustness in stochastic environments while also boosting clean-benchmark performance.
-
MiA-Signature: Approximating Global Activation for Long-Context Understanding
MiA-Signature approximates the global activation state induced by a query via submodular concept selection to enable tractable long-context understanding in LLMs.
-
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
-
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
MICA mixes per-turn and whole-trajectory normalized reward signals to train emotional-support chatbots, outperforming GRPO and REINFORCE++ on EMPA, EQ-Bench, and EmoBench.
-
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.
-
TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.
-
MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation
MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.