pith. sign in

Nudging the boundaries of LLM reasoning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1 cs.CL 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Selective Off-Policy Reference Tuning with Plan Guidance

cs.AI · 2026-05-12 · unverdicted · novelty 6.0 · 2 refs

SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.

AIPO: Learning to Reason from Active Interaction

cs.CL · 2026-05-08 · unverdicted · novelty 6.0 · 2 refs

AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.

citing papers explorer

Showing 2 of 2 citing papers.

  • Selective Off-Policy Reference Tuning with Plan Guidance cs.AI · 2026-05-12 · unverdicted · none · ref 12 · 2 links

    SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.

  • AIPO: Learning to Reason from Active Interaction cs.CL · 2026-05-08 · unverdicted · none · ref 5 · 2 links

    AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.