Pith. sign in

REVIEW 9 cited by

Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding

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 2309.15028 v3 pith:6XBWKF7W submitted 2023-09-26 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords textnetworkpolicysearchvaluedecodingdemonstrategeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Inference-time search algorithms such as Monte-Carlo Tree Search (MCTS) may seem unnecessary when generating natural language text based on state-of-the-art reinforcement learning such as Proximal Policy Optimization (PPO). In this paper, we demonstrate that it is possible to get extra mileage out of PPO by integrating MCTS on top. The key idea is not to throw out the value network, a byproduct of PPO training for evaluating partial output sequences, when decoding text out of the policy network. More concretely, we present a novel value-guided decoding algorithm called PPO-MCTS, which can integrate the value network from PPO to work closely with the policy network during inference-time generation. Compared to prior approaches based on MCTS for controlled text generation, the key strength of our approach is to reduce the fundamental mismatch of the scoring mechanisms of the partial outputs between training and test. Evaluation on four text generation tasks demonstrate that PPO-MCTS greatly improves the preferability of generated text compared to the standard practice of using only the PPO policy. Our results demonstrate the promise of search algorithms even on top of the aligned language models from PPO, and the under-explored benefit of the value network.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference

    cs.SE 2026-05 unverdicted novelty 7.0 of 10

    POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.

  2. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

    cs.AI 2025-10 unverdicted novelty 7.0 of 10

    ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.

  3. Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

    cs.LG 2025-10 conditional novelty 6.0 of 10

    MAHALO aligns LLMs to multiple objectives in one model via per-objective action heads and PRM-guided decoding, improving math, value, and tutoring metrics jointly.

  4. It's Not That Simple. An Analysis of Simple Test-Time Scaling

    cs.LG 2025-07 conditional novelty 6.0 of 10

    The apparent scaling behavior of the s1 model is mostly an artifact of truncating long outputs, while appending 'Wait' does not reliably improve answers.

  5. Breaking the Myth: Can Small Models Infer Postconditions Too?

    cs.SE 2025-07 conditional novelty 6.0 of 10

    Fine-tuning Qwen2.5-Coder-7B on 1.5K reasoning examples yields postcondition generation close to GPT-4o and better than 32B open models on Defects4J.

  6. Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

    cs.AI 2024-08 unverdicted novelty 6.0 of 10

    Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-wor...

  7. Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    CPT shares deduplicated intermediate information across parallel search branches at inference time, yielding a stronger accuracy-latency Pareto frontier than isolated-branch baselines on HMMT and AIME.

  8. From System 1 to System 2: A Survey of Reasoning Large Language Models

    cs.AI 2025-02 accept novelty 3.0 of 10

    The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.

  9. Reinforcement Learning from Human Feedback

    cs.LG 2025-04 unverdicted novelty 2.0 of 10

    The book introduces the origins, mathematical setup, and optimization stages of RLHF including reward modeling, reinforcement learning, rejection sampling, and direct alignment algorithms.

Pith tools