pith. sign in

ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured information that later steps rely on. Recent retrieval-based memory systems surface relevant content but still overlook the causal and logical structure needed for multi-step reasoning. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. Unlike prior context management approaches, ContextWeaver supports: (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summarization that condenses root-to-step reasoning paths into reusable units; and (3) a lightweight validation layer that incorporates execution feedback. On the SWE-Bench Verified and Lite benchmarks, ContextWeaver improves performance over a sliding-window baseline in pass@1, while reducing reasoning steps and token usage. Our observations suggest that modeling logical dependencies provides a stable and scalable memory mechanism for LLM agents that use tools.

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

ECHO: Prune to act, trace to learn with selective turn memory in agentic RL

cs.LG · 2026-06-30 · unverdicted · novelty 6.0

ECHO is a selective turn-memory framework for agentic RL that compresses turns into indexed records, selects them for bounded contexts, and uses source indices to assign outcome credit to supporting evidence, reaching 43.4% accuracy on BrowseComp-Plus versus 28.9% for GRPO and 36.1% for SUPO.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • ECHO: Prune to act, trace to learn with selective turn memory in agentic RL cs.LG · 2026-06-30 · unverdicted · none · ref 35 · internal anchor

    ECHO is a selective turn-memory framework for agentic RL that compresses turns into indexed records, selects them for bounded contexts, and uses source indices to assign outcome credit to supporting evidence, reaching 43.4% accuracy on BrowseComp-Plus versus 28.9% for GRPO and 36.1% for SUPO.