arXiv AI July 17, 2026 By Frank Guo

Why Git Is the Memory Solution for the Agentic Development Lifecycle

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 15

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

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.

By Pavan C Shekar, Abhishek H S, Aswanth Krishnan

llms agents benchmarks

arXiv AI

Jun 10

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

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.

By Liuyin Wang

llms agents benchmarks

arXiv AI

Jun 11

Exploration Structure in LLM Agents for Multi-File Change Localization

arXiv:2606. 11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue.

By Akeela Darryl Fattha, Kia Ying Chua, Lingxiao Jiang, Laura Wynter

llms agents benchmarks

arXiv AI

Aug 7

CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents

arXiv:2608. 05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it.

By Wuya Chen, Yihao yang, Yang Cao, Yue Lin

llms agents reinforcement-learning

Hugging Face Trending Papers

Aug 6

CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents

Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it. On SWE-Bench Verified, a 30B OpenHands agent averages 23 rounds and 631K tokens per resolved issue, with many calls spent on grep, glob, and view_file during repository exploration.

llms agents reinforcement-learning

arXiv AI

Jul 29

Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents

arXiv:2607. 24882v1 Announce Type: cross Abstract: Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task.

By Bowen Qin, Yi Xie

rag agents benchmarks

Related stories

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

Exploration Structure in LLM Agents for Multi-File Change Localization

CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents

CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents

Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents