Top- k Retrieval Leaves Memory Value Undetermined
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents
- Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning
- Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
- PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion
- SPEX: Scaling Feature Interaction Explanations for LLMs
- Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
- Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework
- AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
- Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
- Top-k Combinatorial Bandits with Full-Bandit Feedback
- Effect Aliasing in Observational Studies
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Off-policy evaluation for slate recommendation
- MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
- FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents