Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression

Mingxuan Wang; Fei Luo; Bo Wang; Guorun Yao; Yinglong Guo; Chao Ning; Hongyue Chen; Yanbiao Ma

cs.AISep 23, 2026

Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression

Authors: Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma,

Organizations: TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University

Abstract

Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion for safe compression. Although agent histories exhibit strong low dimensional structure, similar global geometry can preserve very different amounts of task evidence. At identical retained block counts, evidence aware selection raises next action Top 3 retention from 0.31 to 0.69, while centroid similarity remains 0.98. Controlled replacement further shows that action related information can be substantially altered while global geometric measures remain nearly unchanged. Motivated by this gap between geometry and evidence, we introduce Geometry Guided Evidence Preserving Memory (GEM), a training free compressor that protects task and execution evidence before using geometric residuals to complete coverage. GEM reduces mean combined token usage from 2.69M to 2.11M per task, a 21.4% reduction, while maintaining comparable task reward. Our results show that efficient agent history compression should optimize for preserved task evidence rather than geometric coverage alone.

Figures & tables

Figure 1: Structured redundancy in agent histories. Real histories are compared with feature-shift and Gaussian controls. The two representation spaces show the same concentration pattern.

Metric	Geometry	Evidence	$\Delta$
Action projection	0.91	0.94	$\uparrow\,0.03$
Next-action Top-3	0.31	0.69	$\uparrow\,0.38$
Final projection	0.90	0.94	$\uparrow\,0.04$
Goal projection	0.91	0.94	$\uparrow\,0.03$
Centroid similarity	0.98	0.98	$-$

Table 1: Matched-budget retention at 650 checkpoints.

Figure 2: Matched-budget geometry and task information. The trajectory-level visualization contrasts evidence-constrained and geometry-only selection at the same retained block count.

Figure 3: Next-action information across ordered spectral bands.

Metric	$\boldsymbol{\Delta}$
Task information
Action projection	$-0.03$
Next-action Top-3	$-0.33$
Global geometry
Centroid similarity	$+0.00$
Captured energy	$+0.00$

Table 2: Targeted block replacement effects.

Figure 4: Overview of GEM . (a) A frozen encoder represents complete interaction blocks. (b) Evidence constraints form the protected set $\mathcal{P}_{t}$ . (c) Residual geometric completion adds blocks whose directions are not covered by the current selected span. (d) Retained original blocks are reconstructed in chronological order and forwarded to the unchanged agent. The online forwarding constraints are described in Section 5.3 .

Method	Code		Office		Security		Web		Overall
	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$
Base agent	76.99	1.37	81.84	1.20	47.76	5.98	72.14	2.43	69.87	2.69
GEM	75.25	1.35	84.06	1.15	49.56	3.95	72.14	2.09	70.18	2.11

Table 3: WorkBuddyBench Full260 results.

S

denotes mean reward

\times 100

, and

T

denotes combined tokens per task (M). Higher

S

and lower

T

are better.

Method	Code		Office		Security		Web		Overall
Method	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$
Base agent	72.93	1.44	81.64	1.04	44.58	3.97	71.00	1.10	67.54	1.89
Window ( $K=5$ )	66.81	3.12	67.43	3.98	32.32	2.13	59.00	2.58	56.39	2.95
Window ( $K=10$ )	74.37	1.76	73.05	1.82	40.07	0.82	61.00	3.55	62.12	1.99
Window ( $K=20$ )	79.31	1.42	85.11	2.23	40.28	1.13	70.00	3.30	68.67	2.02
Periodic summary ( $n=3$ )	65.44	1.91	67.66	2.14	26.32	0.99	82.66	3.82	60.52	2.21

Table 4: Fixed-40 context-management reference.

S

is mean reward

\times 100

and

T

is combined tokens per task (M). Each domain contains ten tasks.

Variant	Code		Office		Security		Web		Overall
Variant	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$	$S\uparrow$	$T\downarrow$
Base agent	59.79	2.33	74.28	3.02	62.95	10.70	46.00	4.73	60.75	5.19
GEM	70.79	2.52	69.32	3.18	53.45	4.33	48.00	3.41	60.39	3.36
Random completion	47.40	2.72	60.86	5.20	56.69	6.69	47.30	3.23	53.06	4.46
Geometry only	60.93	2.40	59.62	1.25	48.92	8.14	50.64	4.71	55.03	4.12

Table 5: Online 20-task ablation by domain.

S

is mean reward

\times 100

and

T

is combined tokens per task (M). Each domain contains five tasks.

Figure 5: Compression strength. (a) Next-action Top-3 retention at exact retained budgets

K

. (b) Top-3 retention and retained-history ratio as the coverage threshold

\tau

increases. The exact-

K

sweep uses

28

trajectories and

525

common checkpoints; the coverage sweep uses

32

trajectories and

59

checkpoints.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Setting	Value
Minimum complete blocks	16
Coverage target $\tau$ / nominal core capacity $K$	0.90 / 16
Recent / Goal / State / Error limits	4 / 1 / 3 / 2
Error eligibility horizon	8 blocks
Source protection activation	Source-like fraction $\geq 0.50$
Initial-block protection	0

Appendix

Table B.1 : Shared implementation settings across Code, Office, Security, and Web.

Representation	Metric	Real	Feature-shift	Gaussian
Isolated blocks	Effective rank	8.39	16.99	19.96
Isolated blocks	$r_{90}/n$	0.47	0.78	0.88
Selector space	Effective rank	14.04	23.54	30.07
Selector space	$r_{90}/n$	0.48	0.78	0.85

Appendix

Table C.1 : Structured low-dimensionality of agent histories. Values are trajectory medians for centered representations;

r_{90}/n

is the fraction of available blocks required to explain

90\%

of centered energy.

Selector	Action	Final	Goal	Top-3	Centroid
Recent- $K$	0.96	0.88	0.82	0.76	0.97
Random- $K$	0.92	0.92	0.95	0.45	0.99
Cosine Top- $K$	0.86	0.91	0.97	0.53	0.96
Novelty Top- $K$	0.93	0.93	0.96	0.33	0.99
GEM	0.95	0.95	0.96	0.78	0.99

Appendix

Table D.1 : Same-retained-count offline selector comparison on 32 trajectories and 59 checkpoints.

Variant	Retention	Action	Top-3	Centroid
Full constraints	0.46	0.95	0.62	0.99
Geometry only	0.39	0.91	0.25	0.98
Recent + Goal only	0.45	0.95	0.57	0.98
Without State	0.45	0.95	0.53	0.98
Without Error	0.45	0.95	0.56	0.98
All candidates	0.44	0.95	0.59	0.99

Appendix

Table D.2 : Offline component ablation at each variant’s natural retained fraction (32 trajectories, 59 checkpoints).

$K$	Geometry only	Evidence constrained	Recent- $K$	Recent+Goal
8	0.18	0.56	0.50	0.51
9	0.21	0.56	0.53	0.52
10	0.24	0.57	0.55	0.53
11	0.27	0.59	0.54	0.54
12	0.31	0.60	0.56	0.56
13	0.33	0.62	0.58	0.57

Appendix

Table D.3 : Exact retained-count sweep. Values are next-action Top-3 retention on 28 trajectories and 525 checkpoints common to all

K

$\tau$	Retained fraction	Top-3	Action projection
0.85	0.38	0.58	0.94
0.86	0.39	0.58	0.94
0.87	0.41	0.58	0.95
0.88	0.43	0.61	0.95
0.89	0.44	0.62	0.95
0.90	0.48	0.64	0.96

Appendix

Table D.4 : Coverage-threshold sweep on 32 trajectories and 59 checkpoints.

Token category	Base agent	GEM
Uncached input	48.70K	201.48K
Cached input	2.60M	1.82M
Normal output	12.40K	15.68K
Reasoning output	25.38K	22.81K
Model total	2.69M	2.06M
Embedding	0	46.97K

Appendix

Table E.1 : Full260 token composition, mean per task. K and M denote thousands and millions of tokens. Values use the same reporting precision as the main text.

Agent Memory Management

Agent memory management studies how AI agents store, update, retrieve, compress, and forget information across long-running tasks.

See all 447 papers

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
Memory Control Signals Emerge Before Action in Long Horizon Agents
Sep 23, 2026Mingxuan Wang, Guorun Yao, Fei Luo +6Agent Memory Management Long-Horizon LLM Agents
TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University
When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
Sep 24, 2026Mingxuan Wang, Fei Luo, Bo Wang +6Long-Context Modeling Long-Horizon LLM Agents
TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University

Sep 23, 2026J/K move · Enter open · S save

StateComp: Learning When to Compress History in Long Horizon Agents

Mingxuan Wang, Hongyue Chen, Yinglong Guo, Fei Luo+5

TierFlow Team · Gaoling School of Artificial Intelligence, Renmin University of China · Tsinghua University

Context Compression Long-Horizon LLM Agents Agent Memory

Open paper AskPDF arXiv

Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing context management methods largely compress history based on fixed windows, periodic schedules, or current relevance, overlooking a more fundamental question: when has a past interaction become safe to replace? Premature compression may remove information still needed for future actions, while overly conservative retention leads to substantial context overhead. To address this, we propose State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state. StateComp constructs KEEP and READY supervision through a two-stage annotation procedure and trains an imbalance-aware router on hidden representations from a frozen language model. A bounded state representation further reduces the cost of evaluating long histories, while adjacent READY interactions are grouped into continuous spans and replaced with compact summaries during execution. Experiments on WorkBuddyBench show that StateComp reduces total agent and summarization tokens by 52.27% while maintaining task performance, and achieves a 12.67-fold speedup in representation extraction.

Abstract

Agent Memory Management

Explore similar work

StateComp: Learning When to Compress History in Long Horizon Agents

Memory Control Signals Emerge Before Action in Long Horizon Agents

When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression