Magellan — Guided MCTS for Escaping the Gravity Wells of LLM Creativity

Paper. Lufan Chang. Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation. 1st Open Conference on AI Agents for Science (agents4science 2025). Independent Researcher. [arXiv]

0. The Picture in One Paragraph

Ask an LLM to generate a novel idea and it tends to default to high-probability, familiar concepts — the paper’s framing is that generation gets stuck in training-data “gravity wells.” Tree-of-Thoughts-style search tries to escape this by exploring multiple branches, but it relies on the LLM’s own self-evaluation to score and prune those branches — an unprincipled and, empirically, unreliable signal for judging genuine novelty. Magellan reframes creative generation as guided MCTS over an LLM’s latent conceptual space, replacing self-evaluation with a hierarchical guidance system: a semantic compass vector (built via orthogonal projection of concept embeddings) sets the long-range direction of the search toward a promising, non-obvious region of the solution space, while a landscape-aware value function — combining coherence (token log-probability), novelty (semantic distance from established knowledge), and progress (“semantic momentum,” how much new information a step adds relative to its parent) — makes the local, step-by-step tactical decisions inside the UCT selection formula. On a scientific idea generation task, Magellan wins 92% of head-to-head comparisons against zero-shot, CoT, ReAct, and ToT baselines, using only a Qwen3-1.7B backbone.

1. The Problem — Gravity Wells and Unreliable Self-Evaluation

Two separable failures compound in naive creative generation with LLMs:

Gravity wells. Sampling from an LLM’s output distribution over-weights common, familiar concepts from training data — genuine novelty is, almost by definition, lower-probability, so unstructured generation rarely reaches it.
Unreliable self-evaluation. Search-based mitigations like Tree-of-Thoughts try to explore multiple candidate branches and prune with the LLM’s own judgment of which branch is “better” — but an LLM judging its own candidate ideas for novelty and promise is exactly the same distribution-following process that produced the gravity-well problem in the first place, just applied one level up.

2. The Magellan Method

2.1 Semantic compass — global guidance

A semantic compass vector is computed via orthogonal projection of concept embeddings: it is constructed to preserve the core problem context (so the search doesn’t drift off-topic) while maximizing the influence of directions that lead toward novel mechanistic pathways. This vector gives the whole MCTS search a consistent long-range target — a fixed sense of “which direction is interesting” that doesn’t have to be re-derived and re-judged at every node.

2.2 Landscape-aware value function — local guidance

Instead of asking the LLM to self-evaluate each candidate node, a value function combines three explicit, computable terms:

Coherence — average token log-probability, measuring local fluency/plausibility.
Novelty — semantic distance from established (training-data- typical) knowledge.
Progress — “semantic momentum”: how much substantially new information a step introduces relative to its parent node, penalizing branches that just restate or trivially rephrase prior content.

This weighted combination is added directly as a guidance term inside the standard UCT (Upper Confidence bound applied to Trees) selection formula, replacing the role that self-evaluation would otherwise play in choosing which branch to expand next.

3. Results

Evaluated on a scientific idea generation task, judged by an LLM judge (DeepSeek-V3.1-Think) scoring 1–10 on Plausibility, Clarity, and Innovation, with all methods using a Qwen3-1.7B generation backbone:

Method	Plausibility	Clarity	Innovation	Overall	Win rate
Zero-shot	7.98 ± 0.62	8.48 ± 0.68	7.14 ± 0.78	7.87	0.0%
CoT	8.66 ± 0.48	9.48 ± 0.54	7.74 ± 0.49	8.63	8.0%
ReAct	4.58 ± 2.33	4.82 ± 1.65	4.28 ± 2.37	4.56	0.0%
ToT	5.48 ± 1.64	4.30 ± 1.53	5.02 ± 1.65	4.93	0.0%
Magellan	8.98 ± 0.32	9.30 ± 0.54	8.54 ± 0.71	8.94	92.0%

ReAct and ToT score notably below even the zero-shot baseline, with the paper attributing this to “thematic drift” and shallow, repetitive exploration — a pointed illustration of the self-evaluation failure mode Magellan is designed to avoid, though the severity of this gap is worth treating cautiously (see limitations below).

Ablation

Removing the guidance term from the UCT selection formula — i.e., falling back to plain UCT exploration without the semantic compass/value function — drops the win rate from 90.0% to 10.0%, a near-total collapse that indicates the guidance system, not the MCTS scaffolding itself, is doing essentially all of the work.

Efficiency

MCTS is configured for a maximum of 30 iterations, but the search reportedly converges in roughly 3 iterations on average — the guidance signal is precise enough to avoid the kind of broad, unguided exploration that would need many more iterations.

4. Why It Matters

The core claim worth taking seriously is architectural, not just empirical: self-evaluation is not a free source of judgment — asking an LLM to score its own candidate outputs for a property like novelty inherits the same biases that make naive generation gravity-well-prone in the first place. Magellan’s answer — decompose “is this idea good” into explicit, separately-computable signals (fluency, distance-from-known, information-gain-over-parent) rather than one holistic self-judgment — is a pattern that could generalize well beyond scientific idea generation to any LLM-search setting where self-evaluation is currently the default (which includes most ToT/MCTS-for-reasoning systems).

5. Limitations Worth Knowing

Single-author, independent research, evaluated on one domain (scientific idea generation) with one LLM judge — independent replication at larger scale and across different creative domains (e.g., open-ended design, creative writing) would strengthen the claim.
Small backbone (1.7B). Whether the gap over baselines persists, narrows, or widens with a larger generation backbone is untested.
ReAct/ToT baseline failures are unusually severe (overall scores of 4.56 and 4.93, both below zero-shot) — this could reflect a genuine limitation of those methods for this task, but it is also consistent with under-tuned baseline implementations; the magnitude of the gap should be interpreted cautiously until independently reproduced.
LLM-judge evaluation (DeepSeek-V3.1-Think scoring 1–10) inherits whatever biases that judge model has about what counts as “innovative” — a single automated judge is a narrower validation than human expert evaluation on genuinely novel scientific ideas.

6. The Takeaway for a First Reader

If you remember three things:

LLMs default to familiar, high-probability concepts (“gravity wells”), and Tree-of-Thoughts-style self-evaluation is an unreliable way to escape them, since the judge and the generator share the same underlying bias.
Magellan replaces self-evaluation with two explicit guidance signals: a global semantic-compass vector (orthogonal projection of concept embeddings) and a local landscape-aware value function (coherence + novelty + progress) injected directly into MCTS’s UCT formula.
92% win rate against zero-shot/CoT/ReAct/ToT baselines on scientific idea generation with a small 1.7B backbone — and an ablation showing the guidance term, not the search scaffolding, is responsible for nearly all of the gain (90% → 10% win rate when removed).

References

Chang, L. (2025). Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation. 1st Open Conference on AI Agents for Science (agents4science 2025). arXiv:2510.21341.
Related on this site: PriorZero — another MCTS-plus-LLM-guidance system, applied to sequential decision-making rather than creative idea generation; BG-MCTS — budget-aware MCTS for reasoning, a related use of guided search under a different objective.