AI Agent Papers2026

FastContext: Training Efficient Repository Explorer for Coding Agents

Moves repository search into a dedicated exploration subagent that issues parallel read-only READ/GLOB/GREP calls and returns compact file:line citations. Trained (4B–30B) with SFT+RL, it reduces main-agent token use up to ~60% and raises end-to-end success by up to ~5.5%.

Visit Website

Introduction

Oops! Something went wrong

[next-mdx-remote-client] error compiling MDX: Expected a closing tag for `<final_answer>` (5:299-5:313) before the end of `paragraph` 3 | ## Key Findings 4 | - Separation pays: moving exploratory reads outside the solver reduces the main agent's token consumption by up to ~60% while improving end-to-end resolution rates by up to ~5.5% in reported benchmarks. This means the solver keeps a cleaner context window and spends more tokens on planning/editing rather than file hunting. > 5 | - Lightweight, trainable explorers: the paper trains 4B–30B exploration models (bootstrapped with supervised trajectories and refined with task-grounded RL) to optimize for broad first-turn coverage, multi-turn evidence gathering, and precise citation generation. Trained explorers produce compact <final_answer> blocks of file paths and line ranges instead of pasting large code snippets. | ^ 6 | - Practical tool set and workflow: FastContext exposes only read-only tools (READ, GLOB, GREP) and supports parallel tool calls per exploration turn. The intended contract is simple: the main coding agent invokes FastContext for context; FastContext returns focused citations; the main agent edits/tests/answers using that evidence. 7 | More information: https://mdxjs.com/docs/troubleshooting-mdx

Back

Information

Websitearxiv.org
OrganizationsMicrosoft
AuthorsShaoqiu Zhang, Maoquan Wang, Yuling Shi, Yuhang Wang, Xiaodong Gu, Yongqiang Yao, Rao Fu, Shengyu Fu
Published date2026/06/12

More Items

Computer Vision Papers2026

HumanCLAW: Can Vision-Language Models Act Through a Body?

Siyao Li, Jiawei Gu +16

Evaluates whether vision-language models can make actionable decisions for a physical body by decoupling decision-making from low-level motor execution. Introduces HumanCLAW-Bench with 1,218 long-horizon egocentric episodes across 41 indoor scenes and diagnoses a lack of embodied self-awareness in current VLMs.

vision robotics evaluation benchmarks multimodal+2

Natural Language Processing Papers2026

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

Ruizhe Li, Mingxuan Du +2

Measures how agent memory systems miss implicitly associated facts by introducing InMind, a 125-task benchmark with paired controls that separate stored-vs-retrieval vs knowledge gaps. Quantifies a large retrieval-interface blind spot and points to routing as the core open problem.

benchmark evaluation paper LLM NLP+3

Natural Language Processing Papers2026

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Jiangnan Li, Yuqing Li +3

Turns document relevance into an execution prior for agentic corpus interaction: orders documents for sequential ripgrep traversal, seeds promising entry points with query-relevant paragraphs, and reranks grep matches to surface informative excerpts. Improves the accuracy–efficiency frontier on browse QA and reasoning-intensive retrieval.

retrieval RAG reasoning LLM NLP+3