{"total":11,"items":[{"citing_arxiv_id":"2605.18421","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective","primary_cat":"cs.CL","submitted_at":"2026-05-18T13:54:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EvoMemBench evaluates 15 memory methods for LLM agents and finds long-context baselines competitive with no single memory approach working consistently across settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06716","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","primary_cat":"cs.AI","submitted_at":"2026-05-07T03:38:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LLM agent memory is organized into Storage (preserving trajectories), Reflection (refining them), and Experience (abstracting into reusable knowledge) stages driven by needs for long-range consistency, dynamic adaptation, and continual learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00356","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents","primary_cat":"cs.CL","submitted_at":"2026-05-01T02:33:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A lightweight supervised router using frozen-LLM embeddings for memory admission decisions outperforms LLM-based memory managers in both F1 score and latency on the LoCoMo benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14362","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI","primary_cat":"cs.CL","submitted_at":"2026-04-15T19:25:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"APEX-MEM uses property graphs with temporal events, append-only storage, and an agentic retrieval system to reach 88.88% accuracy on LOCOMO QA and 86.2% on LongMemEval, outperforming prior session-aware methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08256","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HyperMem: Hypergraph Memory for Long-Term Conversations","primary_cat":"cs.CL","submitted_at":"2026-04-09T13:43:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HyperMem is a hypergraph memory architecture that groups related conversation episodes and facts via hyperedges and reports 92.73% LLM-as-a-judge accuracy on the LoCoMo benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.02556","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs","primary_cat":"cs.LG","submitted_at":"2026-01-30T13:15:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SEAM learns to generate utility-optimized structured experiences via rollouts to boost frozen LLM performance on mathematical reasoning benchmarks with low overhead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.11100","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReCreate: Reasoning and Creating Domain Agents Driven by Experience","primary_cat":"cs.AI","submitted_at":"2026-01-16T09:00:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ReCreate automatically creates and adapts domain LLM agents by turning past interaction experiences into scaffold edits via reasoning and hierarchical abstraction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.01885","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","primary_cat":"cs.CL","submitted_at":"2026-01-05T08:24:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AgeMem unifies long-term and short-term memory management in LLM agents by exposing memory operations as learnable tool actions trained via three-stage progressive reinforcement learning, outperforming baselines on long-horizon tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.19828","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","primary_cat":"cs.CL","submitted_at":"2025-08-27T12:26:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Memory-R1 uses PPO and GRPO to train a Memory Manager (ADD/UPDATE/DELETE/NOOP) and Answer Agent that together outperform baselines on long-context QA benchmarks after training on only 152 examples.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"retrieved fact is \"Loves to play cricket with friends\", then update the memory with the retrieved fact. Example (b) - if the memory contains \"Likes cheese pizza\" and the retrieved fact is \"Loves cheese pizza\", then do NOT update it because they convey the same information. Important: When updating, keep the same ID and preserve old_memory. - Example: Old Memory: [ {\"id\" : \"0\", \"text\" : \"I really like cheese pizza\"}, {\"id\" : \"2\", \"text\" : \"User likes to play cricket\"} ] Retrieved facts: [\"Loves chicken pizza\", \"Loves to play cricket with friends\"] New Memory: { \"memory\" : [ {\"id\" : \"0\", \"text\" : \"Loves cheese and chicken pizza\", \"event\" : \"UPDATE\", \"old_memory\" : \"I really like cheese pizza\"}, {\"id\" : \"2\", \"text\" : \"Loves to play cricket with friends\", \"event\" : \"UPDATE\", \"old_memory\" : \"User likes to play cricket\"}"},{"citing_arxiv_id":"2507.21046","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","primary_cat":"cs.AI","submitted_at":"2025-07-28T17:59:05+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.15965","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","primary_cat":"cs.IR","submitted_at":"2025-04-22T15:05:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"ChatGPT Memory [18], Apple Intelligence [19], Microsoft Recall [35], Me.bot [36] Open-Source Framework MemoryScope [21], mem0 [20], Memary [37], LangGraph Memory [38], Charlie Mnemonic [39], Memobase [40], Letta [41], Cognee [42] Construction MPC [43], RET-LLM [44], MemoryBank [17], MemGPT [45], KGT [46], Evolving Conditional Memory [47], SECOM [48], Memory3 [49], MemInsight [50] Management MemoChat [51], MemoryBank [17], RMM [52], LD-Agent [53], A-MEM [54], Generative Agents [55], EMG-RAG [56], KGT [46], LLM-Rsum [57], COMEDY [58] Retrieval RET-LLM [44], ChatDB [59], Human-like Memory [60], HippoRAG [13], HippoRAG 2 [61], EgoRAG [62], MemInsight [50] Usage MemoCRS [63], RecMind [64], RecAgent [65], InteRecAgent [66], SCM [67], ChatDev [68],"}],"limit":50,"offset":0}