---
title: TSCG Conservative-Profile Compression
url: https://www.emergentmind.com/topics/tscg-conservative-profile-compression
type: topic
---

# TSCG Conservative-Profile Compression

Searching arXiv for the cited TSCG papers and related conservative-profile terminology.
arXiv search query: "TSCG conservative profile compression tool schema"
TSCG conservative-profile compression is the low-risk deployment setting of TSCG for tool-schema presentation to language models. In the companion TSCG paper, it is not introduced as a standalone formal theory term; the closest exact operational meaning is **TSCG\(_{cons}\) = conservative profile (SDM filler removal only)**, i.e., a restricted deployment that preserves the JSON-to-structured-text representation change while avoiding the more aggressive structural and reordering operators [2605.04107]. In the agentic RAG study, the same profile is evaluated as a **deterministic**, **rule-based**, **structure-preserving** compression of tool schemas that yields about **44–50% token savings** while **preserving descriptions** [2605.26165]. Across both papers, the concept denotes a robustness-first schema-compilation mode whose primary purpose is to reduce schema overhead without destabilizing model-specific schema priors.

## 1. Definition and conceptual scope

TSCG is presented as a deterministic tool-schema compiler operating at the API boundary: production agent systems transmit tool definitions as JSON schemas, but JSON is described as a protocol optimized for machine parsing rather than autoregressive model interpretation [2605.04107]. The conservative profile is therefore not generic prompt compression. It is a schema-aware transformation of tool definitions into token-efficient structured text, applied **pre-tokenization**, externally, and without fine-tuning, model access, or runtime search [2605.04107].

The exact meaning of “conservative” is slightly different across the two main TSCG papers. In the deployment-oriented companion paper, the term is operationalized experimentally as **SDM-only compression** [2605.04107]. In the RAG paper, the term is characterized by its retained content: the conservative profile achieves about **44–50% token savings** while **preserving descriptions**, whereas the balanced profile achieves about **53% compression** by **removing description text and additional schema metadata** [2605.26165]. This suggests that conservative-profile compression is best understood not as a single syntactic normal form, but as the least aggressive TSCG setting that keeps tool-calling semantics intact while minimizing schema perturbation.

A central distinction in the TSCG literature is between three mechanisms: **format translation** from JSON to structured text, **structural reorganization**, and **token reduction** [2605.04107]. Conservative-profile compression retains the first mechanism and centers the third on the safest operator class, while largely suppressing the second.

## 2. Operator basis and restricted transformation regime

The full TSCG framework uses **eight deterministic operators** in a **fixed-order 10-pass pipeline**,
\[
\Pi = \tau_{10} \circ \cdots \circ \tau_1,
\]
with the sequence **Parse, SDM, TAS, DRO, CFL, CFO, CAS, SAD-F, CCP, Emit** [2605.04107]. Conservative-profile compression is defined by restricting this pipeline, in practice, to the safest subset.

The dominant conservative operator is **SDM — Semantic Density Maximization**. Its role is to remove filler tokens and boilerplate, including **104+ patterns** such as politeness markers, hedging, and redundant connectives, under the objective
\[
D(p) = |sem(p)| / |tok(p)|.
\]
The companion paper identifies SDM as **the safest and most robust operator**, and explicitly equates conservative mode with **SDM-only** in key experiments [2605.04107]. The theoretical justification is given by the proposition that removing \(k\) filler tokens from a prompt of length \(n\) increases average effective attention per semantic atom by at least \(n/(n-k)\) [2605.04107].

By contrast, several other operators are treated as risky in conservative deployment. **CFO** and **CFL** are repeatedly reported as harmful at larger catalog sizes; **CCP** adds overhead of about **85–306 tokens** with no measurable average accuracy benefit; **SAD-F** yields negligible or inconsistent gains [2605.04107]. **CAS** is reported as the strongest consistent non-SDM accuracy driver in cross-model ablations, and **DRO** as the main token-saving engine with little direct accuracy effect, but neither is part of the strict conservative default [2605.04107].

A concise deployment taxonomy appears in the implementation guidance:

| Profile | Definition in the papers | Stated deployment role |
|---|---|---|
| Conservative | **SDM only** | Safe default for all local models (4B–32B) |
| Balanced | Full structural compression; appendix lists **SDM, CAS, CFO, DRO, TAS, CCP** | General-purpose higher-compression setting |
| Aggressive | All 8 on Claude; 6 on non-Claude | Frontier-oriented setting |
| Auto | Conservative at **≤20**, balanced sans CFL/CFO at **21–40**, conservative at **>40** | Heuristic policy |

The same appendix also states that **CFL/CFO auto-disabled at \(\geq 30\) tools** in the released implementation [2605.04107]. That implementation detail reinforces the underlying conservative logic: the deployment system itself suppresses structurally disruptive operators as catalog size increases.

## 3. Formal rationale, compression bounds, and the meaning of “conservative”

The main formal compression result in TSCG is Theorem 3.3:
\[
|tok(\Pi(S))| \leq |tok(S)| \cdot \Bigl(1 - \sum_{T_i \in \mathcal{T}_R} r_i \cdot f_i(S)\Bigr),
\]
for a well-formed JSON-Schema tool collection \(S\), where \(r_i\) is the per-token reduction factor and \(f_i(S)\) the fraction of tokens affected by operator \(T_i\) [2605.04107]. The abstract states a formal compression bound of **\(\geq 51\%\)** on well-formed schemas, while the paper reports empirical savings of **61%** in Scenario A, **66%** in BFCL, and **75%** on tool descriptions [2605.04107].

That theorem, however, applies to the full TSCG pipeline rather than specifically to conservative-profile compression. The relevant formal deployment statement is instead the corollary:
\[
\mathrm{Acc}(\mathcal{T}_R(S)) > \mathrm{Acc}((\mathcal{T}_R \cup \mathcal{T}_S)(S))
\]
for models with \(<10B\) parameters, with the recommendation that **conservative profile (\(\mathcal{T}_R\) only) is recommended below 10B** [2605.04107]. The same paper immediately notes a subtle but important mismatch: in the key experimental tables, “conservative profile” is operationalized even more narrowly as **SDM-only**, not the full token-reducing class \(\mathcal{T}_R\) [2605.04107].

This distinction matters for encyclopedia treatment. “Conservative” in TSCG is not simply “maximally lossless compression.” It names a deployment regime that accepts lower compression if that is required to preserve model behavior. The strongest supporting empirical observation is the format-versus-compression decomposition: against JSON baselines, regression yields \(R^2 = 0.88\), but against text baselines it collapses to \(R^2 = 0.03\), which the paper interprets as evidence that representation change is the dominant mechanism for many small models [2605.04107]. A plausible implication is that conservative-profile compression targets the representation mismatch first and treats deeper structural optimization as optional.

## 4. Empirical behavior across models and deployment classes

The strongest direct evidence for conservative-profile compression comes from the small-model and schema-sensitive-model results in the companion paper. In Scenario D, conservative often matches or exceeds balanced compression. For **Mistral 7B**, conservative versus balanced accuracy is **76.0 vs 73.3** at 10 tools, **80.0 vs 80.1** at 20 tools, and **75.3 vs 65.0** at 50 tools. For **Gemma 3 4B**, the corresponding numbers are **80.7 vs 74.7**, **87.3 vs 67.0**, and **87.5 vs 87.4**. For **Qwen3 14B**, conservative yields **98.8 vs 86.2**, **99.3 vs 84.1**, and **95.0 vs 89.6** [2605.04107].

The same pattern appears in parameter extraction. Table 5 reports that conservative beats balanced in **8/9** cases; for **Qwen3 14B**, conservative PF1 is **97.8 / 98.3 / 95.0**, while balanced PF1 is **84.7 / 81.0 / 89.0** [2605.04107]. The paper’s interpretation is explicit: **“This confirms that aggressive structural compression disrupts well-learned schema patterns in strongly fine-tuned models.”** That sentence is close to a canonical statement of the conservative-profile rationale.

Per-operator isolation experiments further organize models into three response classes. **Opus 4.7** is **operator-hungry**: every operator helps, **CCP alone: +20 pp**, **CFL+CFO synergy: +17.5 pp**, and the all-8-operator configuration is optimal. **GPT-5.2** is **operator-sensitive**: **CFL: +2.5 pp**, **CFO: -5 pp**, **CCP: 0 pp**, and **all-8-ops: -10 pp**. **Claude Sonnet 4** is **operator-robust**: **6/7 conditions identical at 80.0%**, with only **CFO causing -2.5 pp** [2605.04107]. Conservative-profile compression is therefore primarily a policy for sensitive or unknown models rather than a universal optimum.

The deployment guidance follows directly. The paper recommends conservative mode for **all models <10B**, **all Qwen architectures**, including **Qwen2.5-Coder 32B**, and as a **safe default for local models 4B–32B** [2605.04107]. Balanced mode remains preferable on some frontier models, but only when operator response has been validated.

## 5. Function under constrained-context agentic RAG

The most systematic evaluation of TSCG conservative-profile compression as an independent intervention appears in the agentic RAG study [2605.26165]. There the problem is formulated as a **tool-context trade-off**: tool schemas, retrieved evidence, system prompt, history, and output all consume the same context window. The paper gives the budget relation
\[
B_{\text{RAG}} = B - B_{\text{sys}} - B_{\text{schema}(f,n)} - B_{\text{hist}} - B_{\text{out}},
\]
and the retrievable chunk count
\[
k = \left\lfloor \frac{B_{\text{RAG}}}{\bar{c}} \right\rfloor
\]
[2605.26165].

Under this formulation, conservative-profile compression is not mainly a quality-enhancement method. It is a budget-reallocation mechanism. In the NovaTech-28 setup, standard JSON schemas cost about **300–500 tokens per tool**, with a 28-tool schema block of about **11,000 tokens**; by contrast, the TSCG conservative profile reduces average schema size from about **393 tokens/tool** to about **197 tokens/tool**, or from **11,295** to **5,670** total tokens at 16K context, i.e. about **49.8%** savings [2605.26165].

The headline phenomenon is the **binary enablement effect** at **8K**. With 28 tools, JSON schemas overflow the context window on **100%** of examples and exact match collapses to **2.6% average** across eight models. Conservative-profile compression restores functionality, raising average EM to **23.1%**, for a **+20.5 pp** average lift across all eight models and **+24.7 pp** among the six exhibiting full enablement [2605.26165]. Individual 8K deltas include **+33** for Llama 3.1:8B, **+31** for Phi-4 14B, **+29** for Mistral-Small 24B, and **+26** for Sonnet 4 [2605.26165].

The paper’s interpretation is strongly budget-driven. At **32K**, where both JSON and TSCG fit, **4 of 5 tested models show \(\Delta \le 1\) pp**, and the effect largely disappears; one exception is **Qwen2.5-Coder:32B**, which improves **+12** with TSCG [2605.26165]. External validation on **HotpotQA** shows the same overflow logic more starkly: **Phi-4 at 8K** goes from **EM = 0.0** with JSON to **EM = 48.0** with TSCG, with schema size reduced from **10,998** to **5,520** and mean retrieval restored to **3.4 chunks** [2605.26165].

Frontier scaling with **Claude Sonnet 4 at 200K** extends the same picture. Fine-grained sweeps show **first chunk loss** at **82 tools** for JSON and **164 tools** for TSCG; **complete overflow** appears at about **494 tools** for JSON and at **>803 tools** for TSCG, extending operational range by **63%** [2605.26165]. The article-level conclusion is that conservative-profile compression becomes infrastructure rather than optimization whenever tool schemas compete directly with retrieval budget.

## 6. Limits, ambiguities, and broader interpretations

The most important limitation is terminological. Neither paper defines a formal named theory object called **“TSCG Conservative-Profile Compression.”** The phrase is partly experimental and partly deployment shorthand [2605.04107]. Moreover, “conservative” is not identical across formal and experimental layers: the corollary recommends a token-reducing conservative set \(\mathcal{T}_R\), while the implemented and benchmarked conservative profile is **SDM-only** [2605.04107].

A second limit is that compression can be harmful once the baseline is already text. In E4 text-baseline experiments for small models, further TSCG compression becomes negative: **Phi-4: -7.0**, **Mistral 7B: -7.4**, **Gemma 3 4B: -8.9**, **Qwen3 4B: -23.4** [2605.04107]. This confines the main use case to settings where the starting point is verbose JSON or where tool-schema tokens materially compete with other context demands.

The formal compression theorem also assumes a **well-formed JSON-Schema tool collection** [2605.04107]. The RAG study adds further operational caveats: its main evaluation uses only the conservative profile; NovaTech-28 is synthetic; retrieval is static rather than dynamic; frontier scaling is reported for one API model; and small models may suffer distractor dilution when compression frees room for many additional chunks [2605.26165].

A broader research interpretation can be drawn, but only by analogy. In numerical methods for compressible flow, conservative multiresolution compression is achieved by sparsifying **cell-average quantities** so that compression and reconstruction preserve conservation exactly [2606.18026]. In event-based covariance transmission, omitted elements are bounded and a decoder-side inflation step reconstructs a conservative upper bound [2403.05977]. These are different domains, but they motivate a common reading of TSCG conservative-profile compression as a **conservation-of-semantics** strategy: compression is acceptable when the reduced representation preserves the structured invariants that downstream computation relies on. In TSCG, those invariants are tool-calling semantics, especially parameter names, parameter types, enum values, type and parameter fidelity, and—under the conservative profile—descriptions [2605.26165].

Under that reading, TSCG conservative-profile compression is a robustness-first schema compilation regime: retain the JSON-to-structured-text representation change, apply only the safest compression primitive by default, and expand beyond that profile only after model-specific validation [2605.04107].

Source: https://www.emergentmind.com/topics/tscg-conservative-profile-compression