# How Much Heavy Lifting Can an Agent Harness Do?: Measuring the LLM's Residual Role in a Planning Agent

arXiv: https://arxiv.org/abs/2604.07236 · HTML: https://mlsanity.com/paper/2604.07236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

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

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)
- [Learning to Play with Intrinsically-Motivated Self-Aware Agents](https://mlsanity.com/paper/1802.07442/) (2018)

## Abstract (arXiv)

Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as much as six times. That raises a question asked less often than it should be: how much of an agent's competence does the harness itself already carry, and how much genuinely still needs the LLM? We externalize a planning harness for noisy Collaborative Battleship into four progressively richer layers -- posterior belief tracking, declarative planning, symbolic reflec tion, and an LLM-backed revision gate -- under a common runtime, taking win rate as the primary metric and F1 as secondary, and pre-specifying heavy lifting as the single largest positive marginal to the primary metric. Across 54 games, declarative pla nning carries the heavy lifting (+24.1pp win rate over a belief-only harness, zero LLM calls); symbolic reflection is mechanistically real but calibration-sensitive, with signed board-level effects up to ±0.140 F1 that cancel on aggregate; and LLM-backed revision ac tivates on only 4.3% of turns with a bounded, non-monotonic effect. The contribution is methodological: once harness layers are made externally measurable, the LLM's role can be quantified as residual rather than assumed central.