# Scaling Laws for Agent Harnesses via Effective Feedback Compute

arXiv: https://arxiv.org/abs/2605.29682 · HTML: https://mlsanity.com/paper/2605.29682/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Scaling Test-time Compute for LLM Agents](https://mlsanity.com/paper/2506.12928/) (2025)
- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [Budget-Aware Tool Use Enables Effective Agent Scaling](https://mlsanity.com/paper/2511.17006/) (2025)
- [Benchmark Test-Time Scaling of General LLM Agents](https://mlsanity.com/paper/2602.18998/) (2026)
- [ContextBench: A Benchmark for Context Retrieval in Coding Agents](https://mlsanity.com/paper/2602.05892/) (2026)
- [Scaling Test-Time Compute for Agentic Coding](https://mlsanity.com/paper/2604.16529/) (2026)
- [Agentic Test-Time Scaling for WebAgents](https://mlsanity.com/paper/2602.12276/) (2026)
- [The Scaling Laws of Skills in LLM Agent Systems](https://mlsanity.com/paper/2605.16508/) (2026)

## Built on by (most cited first, 2 of 2)

- [Memory-Orchestrated Semantic System (MOSS): An Auditable Agentic Memory Architecture](https://mlsanity.com/paper/2607.04391/) (2026)
- [Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination](https://mlsanity.com/paper/2610.05382/) (2026)

## Abstract (arXiv)

Agent harnesses shape language-model performance by controlling tool use, feedback, verification, memory, and repair. Yet raw test-time expenditure, such as tokens, tool calls, wall time, or cost, cannot distinguish useful feedback from redundant or unstable interaction. We introduce Effective Feedback Compute (EFC), a trace-level scaling coordinate for informative, valid, non-redundant, and retained feedback. We further define Estimated-EFC, NRS-EFC, harness efficiency η, and task-demand normalization for realistic traces and heterogeneous tasks. Across synthetic, real, held-out, and prospective evaluations, EFC-based coordinates outperform raw-compute baselines and SAS. Oracle-EFC/Dtask reaches R2=0.99 in controlled scaling, and NRS-EFC/Dtask reaches R2=0.93 on real traces where raw compute has near-zero or negative fit. Finally, ours uses EFC as a companion control layer for existing harnesses, improving mean pass rate from 61.2% to 68.2% while reducing mean raw cost from 213.8 to 85.1 under matched settings. These results suggest that harness scaling depends on durable, task-sufficient feedback rather than raw computation alone.