# AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

arXiv: https://arxiv.org/abs/2605.26596 · HTML: https://mlsanity.com/paper/2605.26596/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 37 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)
- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 9 of 9)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking](https://mlsanity.com/paper/2504.07104/) (2025)

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

- [TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning](https://mlsanity.com/paper/2608.29363/) (2026)
- [REA: From Correct LLM Judgments to Safe Decision Delivery](https://mlsanity.com/paper/2610.17473/) (2026)

## Abstract (arXiv)

The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the compared inference-free and LLM-based methods, AGORA is the only one retaining >= 75% uncompressed performance in 8 of 9 cells (with the lone exception at 73%); a four-way component ablation isolates the structural floor as the dominant quality lever and the learned scorer as the source of 1.0-11.5x adaptive end-to-end compression from a single fixed keep ratio.