When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
cs.AI, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
- SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
- Training Verifiers to Solve Math Word Problems
- When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception
- Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment
- Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics
- Measuring Mathematical Problem Solving With the MATH Dataset
- Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks
- DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains
- DRILL: Training World Models to Improve Policies, Not Predict Pixels
- Understanding Embodied Reference with Touch-Line Transformer
- Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
- Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive 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