arXiv AI October 27, 2026 By Fernando Vallecillos-Ruiz, Islem Bouzenia, Michael Pradel, Leon Moonen

The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents

The paper investigates how deleting portions of a software engineering agent’s past trajectory affects performance and cost. Across 9,400 runs with two state‑of‑the‑art agents, it finds that large deletions (even up to 100% of reasoning text) can maintain overall effectiveness if applied with a delay, but immediate deletion harms performance. The study also shows that cost savings depend on the pricing model: a flat model yields savings in 26 of 42 cases, while a caching‑aware model actually increases costs because it breaks a low‑rate cached prefix.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 7

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.

By Chao Yao, Yangbo Wei, Zhen Huang, Junhong Qian, Chenle Chen, Shaoqiang Lu, Chen Wu, Lei He

llms agents efficiency

arXiv AI

Oct 9

Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice

Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice explores a method where an agent selectively replaces detailed tool results with concise notes while archiving the originals for recovery. Using a Python harness, the approach reduces prompt tokens from 912,492 to 231,951 and cuts cumulative input tokens by 50%, yielding significant API cost savings. However, the method increases request count, slightly slows execution, and its effectiveness varies across different workloads.

By Jan-Peter Franke

agents

arXiv AI

Oct 21

REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents

The paper introduces REM (Reusable Experience Memory), a framework that manages the lifecycle of experience for large language model agents performing long-horizon coding tasks. REM consolidates completed trajectories into compact, phase-structured documents, injects them at task start, and evicts them after a single exposure, making the memory system responsive to the agent’s needs. Experiments on repository-level bug fixing show REM outperforms state‑of‑the‑art memory systems in retrieval accuracy and task resolution while reducing cost.

By Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen, Xiaojing Yu, Cris Liu, Bingqing Song, Bin Xu, Suleiman A. Khan, You-Lin Chen

llms agents benchmarks

arXiv AI

Oct 15

Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users...

By Bofan Xie, Chaokun Wang, Guanchen Ge, Songyao Wang, Fang Niu, Hang Zhang, Wei Wang

llms agents benchmarks

arXiv AI

Aug 14

Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories

arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.

By Yifei Li, Heng Wang, Lingling Zhang, Muye Huang, Xinyu Zhang, Jiashuai Liu, Hang Yan, Rongman Xu

rag agents

arXiv AI

Oct 15

TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents

arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this...

By Pramod Kumar, Raj Kumar Pandey

llms agents

One email a morning, machine-written

Related stories

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice

REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents

Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories

TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents