ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression

Xiafeng Man; Siyuan Ye; Xiaosong Ma

cs.CLSep 26, 2026

ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression

Authors: Xiafeng Man, Siyuan Ye, Xiaosong Ma

Organizations: College of Future Information Technology Fudan University Shanghai, China · Department of Computing The Hong Kong Polytechnic University Hong Kong, China

Abstract

While Large Language Model (LLM)-based agents demonstrate strong capabilities in long-horizon tasks by interleaving reasoning with external environment interactions, the continuous accumulation of context rapidly creates a critical memory bottleneck. Existing memory compression methods rely on task-specific optimization or external auxiliary models, introducing significant computational overhead. Furthermore, the resulting compressed representations tend to lose structured relationships, leading to information dilution, attention collapse, and degraded decision consistency. To address these limitations, we propose Auto-Regressive State Machine (ARSM), a lightweight training-free framework that enables in-situ reasoning compression through structured state evolution. ARSM introduces two key components: (i) a trajectory abstraction mechanism that reorganizes interaction histories into compact Hypothesis-Action-Result (HAR) micro-chains; (ii) a dynamic state machine that regulates hierarchical memory through atomic operations and a compression-control parameter. These components are unified within an auto-regressive, self-compressive generation space, where each model output jointly performs external action execution and internal state updates. We evaluate ARSM on Webshop, Multi-Objective Multi-Hop QA, and SWE-Bench Lite datasets. Experimental results show that ARSM maintains the task performance while simultaneously reducing token consumption, offering a practical, cost-effective route toward scalable autonomous agents for long-horizon tasks.

Figures & tables

Figure 1: Overview of the dual-loop architecture. It contains two cyclical processes: (i) execution loop, which manages direct interactions with external tools and feeds back environmental output; and (ii) state evolution loop, which synchronizes agent’s cognition with ARSM. The Auto-Regressive Self-Compressive Space acts as a unified generation space, dispatching tool-call action to the environment and evolution metadata to drive ARSM’s inner state update:

\text{State}_{t-1}\rightarrow\text{State}_{t}

Figure 2: Workflow of trajectory abstraction. The agent performs in-situ compression: previous raw observations are evaluated and distilled into concise results.

Figure 3: State transition mechanism. The model’s structured generation space is parsed to yield a discrete routing signal

u_{t}

, mapping to the branches. Targeted atomic operators are then dynamically applied to update their respective layers, while unaffected subspaces remain frozen.

Method	Training-Free	Self-Contained	Plug-and-Play	Generality
Search-R1	$\times$ (RL)	✓	$\times$	$\times$ (QA)
MEM1	$\times$ (RL)	$\times$ (RAG)	$\times$	$\circ$
ContextBudget	$\times$ (RL)	✓	$\times$	$\circ$
Agent-FLAN	$\times$ (SFT)	✓	$\times$	$\circ$
Mini SWE-Agent	✓	✓	✓	$\times$ (Code)
SE-Agent	✓	✓	✓	$\times$ (Code)

Table 1: Comparison of training costs, structural dependencies, and generalizability across methods. “

\circ

” indicates that the generality requires task-specific training.

Method	Reward $\uparrow$	Peak Token (k) $\downarrow$	Total Token (k) $\downarrow$
Qwen2.5-7B-Instruct	0.2858	5.41 ± 2.40	63.24
Agent-FLAN-7B (SFT)	0.2342	5.84 ± 1.61 ( $\uparrow$ 7.9%)	63.26 ( $\uparrow$ 0.03%)
MEM1-Webshop (Qwen, RAG+RL)	0.1528	1.55 ± 0.14 ( $\downarrow$ 71%)	21.82 ( $\downarrow$ 65%)
ARSM (Qwen-7B, $\rho=0.3$ )	0.4906	3.61 ± 0.87 ( $\downarrow$ 33%)	21.46 ( $\downarrow$ 66%)
ARSM (Qwen-7B, $\rho=0.5$ )	0.4641	3.01 ± 0.47 ( $\downarrow$ 44%)	23.11 ( $\downarrow$ 63%)
ARSM (Qwen-7B, $\rho=0.7$ )	0.4186	2.51 ± 0.23 ( $\downarrow$ 54%)	20.88 ( $\downarrow$ 67%)

Table 2: Performance on WebShop.

Method	$\Sigma_{\mathrm{EM}}$ $\uparrow$	$\Sigma_{\mathrm{F1}}$ $\uparrow$	Peak Token (k) $\downarrow$	Total Token (k) $\downarrow$
Qwen2.5-14B-Instruct	0.567	0.703	3.84	N/R
Search-R1 (RL)	0.009	0.011	2.09 ( $\downarrow$ 46%)	N/R
MEM1-QA (14B, truncate)	0.44	0.50	1.19 ( $\downarrow$ 69%)	N/R
ContextBudget 1 1 1 ContextBudget reports only the context budget; therefore, we use it as its peak token usage. (30B, w/o RL)	0.17	N/R	8.00 ( $\uparrow$ 108%)	N/R
ARSM (14B, $\rho=0.3$ )	1.85	2.15	0.78 ( $\downarrow$ 80%)	55.06
ARSM (14B, $\rho=0.5$ )	1.87	2.30	0.81 ( $\downarrow$ 79%)	54.09

Table 3: Performance on Multi-Objective Multi-Hop QA (16-Objective). N/R denotes results that were not reported in the original work.

Method	Qwen3.5-9B			Qwen3.5-27B
Method	Pass@1 $\uparrow$	Pass@5 $\uparrow$	Token (M) $\downarrow$	Pass@1 $\uparrow$	Token (M) $\downarrow$
Mini SWE-Agent	26.6%	47.5%	6.57	51.7%	1.74
SE-Agent 2 2 2 We were unable to complete the evaluation for SE-Agent; its complex system prompts and tool-calling requirements overwhelmed the models, consistently resulting in format errors or empty patches. (Evolution)	15.0%	N/A	N/A	N/A	N/A
SWE-Pruner (Auxiliary)	40.7%	58.7%	2.29 ( $\downarrow$ 65%)	45.0%	2.37 ( $\uparrow$ 36%)
ARSM ( $\rho=0.1$ )	29.7%	46.67%	2.40 ( $\downarrow$ 63%)	46.5%	0.92 ( $\downarrow$ 47%)
ARSM ( $\rho=0.5$ )	26.2%	44.5%	2.05 ( $\downarrow$ 69%)	46.0%	0.84 ( $\downarrow$ 52%)

Table 4: Performance on SWE-Bench Lite.

Figure 4: Efficiency analysis on SWE-Bench Lite using Qwen3.5-27B. It illustrates the distribution of tokens and interaction turns. Our ARSM (

\rho=0.5

) consistently shifts the distribution towards the left, demonstrating higher efficiency compared to baselines.

Figure 5: Performance and efficiency comparison across different ARSM compression-control parameter (

\rho

) and baselines using Qwen3.5-27B. ARSM drastically reduces prompt token usage compared to SWE-Agent and SWE-Pruner across all evaluated compression rates.

Routing Signal	Ongoing	Milestone	Failure	Success
Percentage (%)	76.34	8.99	9.17	5.50

Table 5: Distribution of routing signals on SWE-Bench Lite, Qwen3.5-9B.

Method	HAR	SM	Reward $\uparrow$	Peak Tokens (k) $\downarrow$	Total Tokens (k) $\downarrow$
Plain Summary	$\times$	$\times$	0.3305	3.63 ± 0.84	44.71
Structured Summary	$\times$	$\times$	0.1321	1.37 ± 0.10	18.44
HAR-only	✓	$\times$	0.4240	3.18 ± 1.86	28.92
SM-only	$\times$	✓	0.3178	2.74 ± 0.23	24.18
ARSM ( $\rho=0.5$ )	✓	✓	0.4899	2.97 ± 0.45	22.84

Table 6: Trajectory summarization and state machine (SM) evolution on 200 Webshop instances. It highlights the complementary roles of HAR abstraction and dynamic state evolution in balancing task performance and token efficiency.

Metric	Score $\uparrow$	Interpretation
State Fidelity	76.1%	Factual faithfulness of compressed states
State Sufficiency	81.4%	Retention of information needed later
Routing Correctness	73.2%	Correctness of routing signals
Trajectory Coherence	72.5%	Global consistency across the trajectory

Table 7: Trajectory-level evaluation of ARSM state updates and routing decisions on 100 WebShop trajectories with

\rho=0.5

. Higher scores indicate better performance.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Efficiency analysis on SWE-Bench Lite using Qwen3.5-9B.

Figure 7: Performance and efficiency comparison across different compression-control parameters (

\rho

) and baselines using Qwen3.5-9B.

Figure 8: Intersections of resolved SWE-Bench Lite instances on Qwen3.5-9B model.

Figure 9: Intersections of resolved SWE-Bench Lite instances on Qwen3.5-27B model.

Model	Union Solved	Solved by All $\rho$	Long-Tail Coverage
Qwen3.5-9B	142	25	48 cases / 18 patterns
Qwen3.5-27B	190	48	94 cases / 90 patterns

Appendix

Table 8: Solved-set overlap of ARSM across different

\rho

settings.

Instance	$\rho=0.2$	$\rho=0.5$	$\rho=0.8$
django__django-16408	151	300	207

Appendix

Table 9: Trajectory length comparison under different compression-control parameters.

$\rho=0.2$	$\rho=0.5$	$\rho=0.8$
Recent raw interaction remains broad and preserves more direct traces of earlier file-reading failures, exploratory inspection, and repeated attempts to understand the relation structure around FilteredRelation.	Recent raw interaction is still available, but it is more selective; repeated low-value inspection is progressively displaced by folded state, and the retained raw messages are increasingly concentrated on specific subproblems such as join reuse and multi-level relation resolution.	Recent raw interaction is narrower still; the visible raw context is more sharply localized to the current debugging hypothesis, while earlier exploration is no longer exposed directly and instead survives primarily through structured memory.

Appendix

Table 10: Qualitative comparison of recent raw memory. As

\rho

increases, the raw interaction surface becomes more selective and more localized to the current subproblem.

$\rho=0.2$	$\rho=0.5$	$\rho=0.8$
# Pitfall - The file-reading commands are producing malformed output; need a more reliable reading method. - Need to use grep or targeted inspection to locate FilteredRelation first. - The problem likely concerns how filtered relation paths are resolved in the ORM.	# Pitfall - The fix needs to be in setup_joins so that existing joins are reused when the field is already part of a FilteredRelation path. - The single-level fix is insufficient; nested paths such as tournament_pool. tournament require the second-level relation to use the correct join. - The necessary information may need to be propagated through the relation metadata structure rather than patched only at the surface.	# Pitfall - The current fixes address part of the join path but still cache the intermediate object on the wrong model. - The issue appears deeper in how nested filtered relations are represented in the relation chain. - Submission may need to avoid unrelated test edits and focus on source-level correction only.

Appendix

Table 11: Representative internal-state excerpts. As compression increases, more of the long-range reasoning trace is preserved through structured pitfalls instead of direct transcript replay.

LLM Agent Memory

Large language model agent memory lets agents retain, organize, retrieve, and update information across interactions and long-running tasks.

See all 376 papers

LightThinker++: From Reasoning Compression to Memory Management
Apr 4, 2026Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7Memory Management for LLM Agents Efficient Language Model Reasoning
Zhejiang University · Ant Group
StateComp: Learning When to Compress History in Long Horizon Agents
Sep 23, 2026Mingxuan Wang, Hongyue Chen, Yinglong Guo +6Context Compression Long-Horizon LLM Agents
TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
May 23, 2026Yuyang Hu, Hongjin Qian, Shuting Wang +5Long-Horizon Agent Tasks Agent Memory Management
GSAI, Renmin University of China · Beijing Academy of Artificial Intelligence

Apr 4, 2026J/K move · Enter open · S save

LightThinker++: From Reasoning Compression to Memory Management

Yuqi Zhu, Jintian Zhang, Zhenjie Wan, Yujie Luo+6

Zhejiang University · Ant Group

Memory Management for LLM Agents Efficient Language Model Reasoning CoT Compression LLM Inference Acceleration Agent Memory Management Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations. However, static compression often struggles with complex reasoning where the irreversible loss of intermediate details can lead to logical bottlenecks. To address this, we evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management. This paradigm shifts to behavioral-level management by incorporating explicit memory primitives, supported by a specialized trajectory synthesis pipeline to train purposeful memory scheduling. Extensive experiments demonstrate the framework's versatility across three dimensions. (1) LightThinker reduces peak token usage by 70% and inference time by 26% with minimal accuracy loss. (2) In standard reasoning, LightThinker++ slashes peak token usage by 69.9% while yielding a +2.42% accuracy gain under the same context budget for maximum performance. (3) Most notably, in long-horizon agentic tasks, it maintains a stable footprint beyond 80 rounds (a 60%-70% reduction), achieving an average performance gain of 14.8% across different complex scenarios. Overall, our work provides a scalable direction for sustaining deep LLM reasoning over extended horizons with minimal overhead.

Abstract

LLM Agent Memory

Explore similar work

LightThinker++: From Reasoning Compression to Memory Management

StateComp: Learning When to Compress History in Long Horizon Agents

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent