memory-evolution

Tag

Cards List
#memory-evolution

CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning

arXiv cs.AI · 4d ago Cached

CHIME is a credit-aware hierarchical memory framework that separates planning and execution memory banks to improve long-horizon agentic planning by accurately attributing task outcomes and outperforming baselines.

0 favorites 0 likes
#memory-evolution

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Hugging Face Daily Papers · 2026-08-25 Cached

The paper introduces Recuris, a recursive memory architecture that improves long-horizon agent success by tracking progress and guiding skill selection through localized, validation-gated updates.

0 favorites 0 likes
#memory-evolution

SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL

arXiv cs.CL · 2026-08-14 Cached

This paper proposes SDAM, a memory-based framework for complex Text-to-SQL that uses structure-difference aware reasoning, contradiction-aware reflection, and schema-grounded memory evolution to improve SQL generation. Experiments show modest gains on BIRD-dev and Spider-test benchmarks.

0 favorites 0 likes
#memory-evolution

RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation

arXiv cs.AI · 2026-07-29 Cached

Introduces RSMeM, a knowledge-enhanced memory evolution mechanism for remote sensing agents that bootstraps LLMs with domain knowledge and iteratively integrates failure experience to improve multi-step tool execution, achieving 6% accuracy gain on DeepSeek-V3.2 with minimal additional tokens.

0 favorites 0 likes
#memory-evolution

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Hugging Face Daily Papers · 2026-06-11 Cached

EvoArena introduces a benchmark for evaluating LLM agents in dynamic environments with progressive updates across terminal, software, and social domains, while EvoMem proposes a patch-based memory paradigm that records structured evolution; experiments show current agents achieve only 39.6% accuracy on EvoArena, and EvoMem yields average gains of 1.5% on the benchmark and improvements on GAIA and LoCoMo.

0 favorites 0 likes
#memory-evolution

SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs

arXiv cs.CL · 2026-06-01 Cached

SAGE proposes a novelty gate for memory evolution in agentic LLMs, using a von Mises-Fisher-based density estimator to decide whether to add, merge, or ignore new facts, reducing LLM calls while maintaining memory quality.

0 favorites 0 likes
← Back to home

Submit Feedback