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
MEM1: learning to synergize memory and reasoning for efficient long-horizon agents.CoRR, abs/2506.15841
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
years
2026 19representative citing papers
Agent-BRACE improves LLM agent performance on long-horizon partially observable tasks by 5.3-14.5% through a decoupled belief state of verbalized atomic claims with certainty labels that keeps context length constant.
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%.
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.
MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
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.
Long-horizon enterprise AI agents' decisions decompose into four measurable axes, with benchmark experiments on six memory architectures revealing distinct weaknesses and reversing a pre-registered prediction on summarization.
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.
CTM-AI combines a formal consciousness model with foundation models to report state-of-the-art results on sarcasm detection, humor, and agentic tool-use benchmarks.
Deterministic Projection Memory (DPM) delivers stateless, deterministic decision memory for enterprise AI agents that matches or exceeds summarization-based approaches at tight memory budgets while improving speed, determinism, and auditability.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
A lightweight RL policy called ContextCurator curates context for frozen LLM agents by reducing noise and keeping reasoning anchors, raising success rates on WebArena (36.4% to 41.2%) and DeepSearch (53.9% to 57.1%) while cutting token use substantially, with a 7B model matching GPT-4o performance.
MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.
AnomalyAgent uses tool-augmented reinforcement learning with self-reflection to generate realistic industrial anomalies, achieving better metrics than zero-shot methods on MVTec-AD.
STEP-HRL enables step-level learning in LLM agents via hierarchical task structure and local progress modules, outperforming baselines on ScienceWorld and ALFWorld while cutting token usage.
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
Opal enables private long-term memory for personal AI by decoupling reasoning to a trusted enclave with a lightweight knowledge graph and piggybacking reindexing on ORAM accesses.
Full-horizon planning with on-demand replanning achieves accuracy parity with single-step planning in tool-calling agents for knowledge base and multi-hop question answering while consuming 2-3 times fewer tokens.
The paper surveys the conceptual foundations, methodological innovations, challenges, and future directions of agentic reinforcement learning frameworks that embed cognitive capabilities like meta-reasoning and self-reflection into LLM-based agents.
citing papers explorer
-
Opal: Private Memory for Personal AI
Opal enables private long-term memory for personal AI by decoupling reasoning to a trusted enclave with a lightweight knowledge graph and piggybacking reindexing on ORAM accesses.