Pith. sign in

REVIEW 7 cited by

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.02508 v3 pith:A647E6PN submitted 2025-02-04 cs.CL cs.AI

classification cs.CLcs.AI
keywords reasoningcapabilitiesllmsmodelssatoriautoregressivechain-of-action-thoughtcoat
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. This typically involves extensive sampling at inference time guided by an external LLM verifier, resulting in a two-player system. Despite external guidance, the effectiveness of this system demonstrates the potential of a single LLM to tackle complex tasks. Thus, we pose a new research problem: Can we internalize the searching capabilities to fundamentally enhance the reasoning abilities of a single LLM? This work explores an orthogonal direction focusing on post-training LLMs for autoregressive searching (i.e., an extended reasoning process with self-reflection and self-exploration of new strategies). To achieve this, we propose the Chain-of-Action-Thought (COAT) reasoning and a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning. Our approach results in Satori, a 7B LLM trained on open-source models and data. Extensive empirical evaluations demonstrate that Satori achieves state-of-the-art performance on mathematical reasoning benchmarks while exhibits strong generalization to out-of-domain tasks. Code, data, and models are fully open-sourced.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL

    cs.AI 2025-09 conditional novelty 6.0 of 10

    DRER rewards CoT trajectories that increase the model's likelihood of the correct answer, plus a length penalty, and the new LogicTree benchmark reportedly lifts a 7B model's average accuracy from 0.13 to 0.60.

  2. AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

    cs.LG 2025-06 conditional novelty 6.0 of 10

    AdapThink is an RL post-training framework that adaptively reduces overthinking and underthinking in reasoning language models by rewarding confidence-appropriate reasoning depth and diverse training samples.

  3. Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A 32B model trained to self-evolve patch candidates through RL reaches 41.6% on SWE-Bench Verified with 50 samples, comparable to a 70B model using 500 samples.

  4. Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

    cs.AI 2026-02 conditional novelty 5.0 of 10

    BAO, a behavior-enhanced SFT plus regularized RL pipeline, improves proactive agents' task performance while lowering user-involvement rate, beating UserRL baselines on three UserRL gym tasks.

  5. Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games

    cs.LG 2025-05 reject novelty 5.0 of 10

    A group, fuse, and retrain recipe for multi-game reinforcement learning lets a 32B model reach near-Claude3.5 performance on several TextArena games, though the headline score is internally inconsistent.

  6. Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

    cs.CL 2025-02 reject novelty 4.0 of 10

    Small LLMs with compute-optimal test-time scaling can outperform much larger models on math benchmarks, but the reported strategy is selected on the same test sets used for evaluation.

  7. A Survey on Large Language Models for Mathematical Reasoning

    cs.AI 2025-06 conditional novelty 1.0 of 10

    Recent advances in LLM mathematical reasoning are organized into comprehension and generation phases, covering methods from prompting to test-time scaling.

Pith tools