# Agents Don't Paginate: First-Chunk Selection for LLM Tool Responses

arXiv: https://arxiv.org/abs/2608.26130 · HTML: https://mlsanity.com/paper/2608.26130/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 7 of 7)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [Extending ResourceLink: Patterns for Large Dataset Processing in MCP Applications](https://mlsanity.com/paper/2510.05968/) (2025)

## Built on by (most cited first, 1 of 1)

- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that routinely exceed the agent's per-turn token budget. The standard remedy, pagination, is available in every protocol that produced these responses; yet across the corpus of session logs from a public Model Context Protocol middleware we observed no agent-initiated requests for a second chunk. The first chunk is what the agent reads, so we ask how often the gold item (the one the agent needs) is placed first in it: the precision-at-1 rate p1. In a controlled offline benchmark we treat first-chunk selection as a 0/1 knapsack and compare six value functions on 500 SWE-bench Verified tasks, then test whether p1 matters with a single-turn file-localisation probe on five language models (4,800 LLM calls; not an end-to-end resolve-rate test). Two pre-registered hypotheses did not hold and are our main findings. The central one is negative: raising p1 does not systematically raise downstream accuracy. Per-model deltas stay under three percentage points (p.p.), are not consistently signed, and no model is significant; the agent recovers the gold from anywhere in the chunk, so what reaches its answer is first-chunk inclusion, not the gold's rank within it. The second: adding four file-metadata signals to a keyword scorer hurts p1 by 4.8 p.p. (paired significance test, p = 0.001). A parameter-free keyword scorer does raise p1, from a 24.2% baseline to 35.0% (+10.8 p.p., far beyond chance; p = 3.9 × 10-8), and to 35.8% with a fallback to the tool's native ordering when no keyword matches. But by our central finding this is a rank-1 gain, and rank-1 is the part that does not reach the agent's answer: downstream accuracy does not move.