arXiv:2606. 14470v1 Announce Type: new Abstract: Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited.
arXiv:2607. 14390v1 Announce Type: cross Abstract: Coding agents now produce a growing share of a team's code, while the reasoning behind each change -- the alternatives weighed, the constraints discovered, the approaches rejected -- is trapped in assistant transcripts that vanish with the session.
APEX-EM is a non‑parametric experience memory that stores full procedural‑episodic traces in a typed Procedural Knowledge Graph and retrieves them via semantic search, structural‑signature matching, and graph traversal. It uses a Plan‑Retrieve‑Generate‑Iterate‑Ingest workflow to produce, quality‑gate, and commit experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. Evaluations on five benchmarks with a shared GPT‑4o backbone show significant performance gains, such as +7.6 pp on BigCodeBench transfer and +1.4 pp on Lifelong Agent Bench, demonstrating that the memory adds to model capability rather than replacing it.
The paper evaluates a deterministic supersession memory, MemStrata, for retrieval‑augmented generation (RAG) systems on real software history. Using 707 GitHub issues, the authors extracted 130 clean atomic state transitions where a single value changes from pre‑fix to post‑fix. MemStrata achieved 0.91 answer accuracy versus 0.57–0.59 for standard RAG, eliminating stale‑fact errors that RAG returned 36–38% of the time, while maintaining comparable retrieval latency.
arXiv:2606. 09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate.
Mnemon is a memory agent that stores conversations as raw, dated records and uses a fast System 1 decision model (Jev) to quickly judge the relevance of records, while a slow System 2 LLM plans searches and composes answers. The agent consolidates records into topic timelines and value histories in the background, enabling efficient retrieval without rewriting conversations into structured formats. Experiments show Mnemon achieving high scores on LoCoMo and LongMemEval‑S with low context length and cost, and Jev outperforming LLMs in evidence separation and speed.
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
arXiv:2609.25054v1 Announce Type: new Abstract: For a long-horizon LLM agent, the memory question is not what was once recorded but what \emph{currently holds}. Most designs answer it only indirectly...
arXiv:2608. 04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it.
arXiv:2606. 01435v1 Announce Type: new Abstract: LLM-based memory systems increasingly maintain facts that evolve over time, where a recurring failure is conflict resolution: when a fact has multiple contradictory values, which should the agent return?
arXiv:2609. 05339v1 Announce Type: new Abstract: Model upgrades are routine; memory migrations are not.
arXiv:2609.23570v1 Announce Type: cross Abstract: Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluatio...
The paper investigates how machine‑learning models can determine whether a claim (a test assertion) remains valid after a code change. It compares two questioning strategies: asking whether a diff preserves behavior versus asking whether a specific claim still holds. The authors find that the latter approach yields far higher precision (up to 0.974) across models of varying cost, while the former performs poorly (precision 0.291–0.329). They also benchmark against a regression‑test selector, showing that even near‑complete knowledge of a change’s reach does not reliably identify falsified claims. The study is grounded in 10,369 mined claims with 184 execution‑verified flips from 23 Python libraries.