AI Paper Atlas

Research map / Large language models / Agents, code and math

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation

Jim Maar, Denis Paperno, Callum Stuart McDougall, Neel Nanda

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
patch activations of attention heads L30H03 and L31H15 with their steered values (instead of full steering) (ablation)Gemma2 9B-it rhyme steering · Rhyme circuit couplets% of steering logit difference recovered: 59%-93%Improved
patch the two heads on the brick couplet (ablation)Gemma2 9B-it · Couplet 1 (reddish brick)logit difference: -2.6 -> 4.61 (steered 5.48)Improved
patch the two heads on the pain couplet (ablation)Gemma2 9B-it · Couplet 2 (striking pain)logit difference: -3.37 -> 1.47 (steered 4.77)Improved
patch the two heads on the bird's wing couplet (ablation)Gemma2 9B-it · Couplet 3 (bird's wing)logit difference: -14.5 -> 2.06 (steered 3.39)Improved
patch the two heads on the ancient guardians couplet (ablation)Gemma2 9B-it · Couplet 4 (ancient guardians)logit difference: -4.94 -> -1.07 (steered 0.93)Improved
steer on the newline token instead of the last word of the first line (ablation)Gemma2 9B and Gemma3 27B · Rhyme family steering effectivenessfraction target rhyme familyHurt
increase model sizeGemma2/Gemma3/Qwen3/Llama3 families · Rhyming and planning metricsrhyme rate and planning metricsImproved
use instruction-tuned instead of base modelGemma2/Gemma3/Qwen3/Llama3 families · Rhyming and planning metricsrhyme rate and planning metricsImproved
ablate attention to both last word and newline token (ablation)Gemma3 27B · Rhyming datasetfraction correct rhyme family and regenerationHurt
ablate attention to only one of last word or newline token (ablation)Gemma3 27B · Rhyming datasetfraction correct regenerationHurt
steer with SAE latent decoder difference (latents 14069 and 5862) instead of mean activation differenceGemma2 9B-it · -eep to -ight rhyme steeringrollouts with target rhyme: 832 out of 1000Improved
steer toward specific word (night/light) instead of rhyme familyGemma2 9B and Gemma3 27B · Specific word steeringword probability change: at most 20 percent for Gemma2 9B and 50 percent for Gemma3 27BMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy