Pith. sign in

REVIEW 15 cited by

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

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 2309.11489 v3 pith:XQU2KGED submitted 2023-09-20 cs.LG cs.AIcs.CLcs.RO

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

classification cs.LG cs.AIcs.CLcs.RO
keywords rewardtext2rewardcodesdensefunctionslanguagelocomotionpolicies
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework that automates the generation and shaping of dense reward functions based on large language models (LLMs). Given a goal described in natural language, Text2Reward generates shaped dense reward functions as an executable program grounded in a compact representation of the environment. Unlike inverse RL and recent work that uses LLMs to write sparse reward codes or unshaped dense rewards with a constant function across timesteps, Text2Reward produces interpretable, free-form dense reward codes that cover a wide range of tasks, utilize existing packages, and allow iterative refinement with human feedback. We evaluate Text2Reward on two robotic manipulation benchmarks (ManiSkill2, MetaWorld) and two locomotion environments of MuJoCo. On 13 of the 17 manipulation tasks, policies trained with generated reward codes achieve similar or better task success rates and convergence speed than expert-written reward codes. For locomotion tasks, our method learns six novel locomotion behaviors with a success rate exceeding 94%. Furthermore, we show that the policies trained in the simulator with our method can be deployed in the real world. Finally, Text2Reward further improves the policies by refining their reward functions with human feedback. Video results are available at https://text-to-reward.github.io/ .

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

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

  1. SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

    cs.AI 2026-05 accept novelty 8.0

    SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.

  2. SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

    cs.AI 2026-05 unverdicted novelty 8.0

    SimWorld Studio uses a self-evolving coding agent to generate adaptive 3D environments that improve embodied agent performance, with reported gains of 18 points over fixed environments in navigation tasks.

  3. Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning

    cs.CL 2026-05 unverdicted novelty 7.0

    Iterative search over reward functions with ranked feedback in GRPO training improves LLM math reasoning, achieving F1 of 0.795 on GSM8K versus 0.609 for baseline.

  4. Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning

    cs.CL 2026-05 accept novelty 7.0

    Iterative LLM-driven search over reward functions, screened via GRPO on GSM8K, raises F1 from 0.609 baseline to 0.795 with ensembles on Llama-3.2-3B.

  5. PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models

    cs.CL 2026-03 unverdicted novelty 7.0

    PR-CAD unifies text-to-CAD generation and editing via progressive refinement with LLMs, a new interaction dataset, and RL-enhanced reasoning to achieve better controllability and faithfulness.

  6. Automatic Generation of High-Performance RL Environments

    cs.LG 2026-03 conditional novelty 7.0

    Closed-loop prompt-based translation with hierarchical verification and iterative repair produces equivalent high-performance RL environments across five cases including new TCGJax.

  7. VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

    cs.RO 2023-07 unverdicted novelty 7.0

    VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.

  8. DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    DriveJudge combines VLM reasoning with rule functions on a new 33,577-sample human-annotated dataset, outperforming EPDMS by 21.23 AUC on quality classification and DriveCritic by 6.5% on trajectory preference.

  9. From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

    cs.LG 2026-05 unverdicted novelty 6.0

    Demo2Reward optimizes VLM reward model language instructions at test time from a few demonstrations to reduce false positives and enable policy learning in simulated and real robotic tasks without manual reward design.

  10. EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models

    cs.RO 2026-05 unverdicted novelty 6.0

    EvoNav automates the design of reward functions for RL robot navigation by evolving LLM proposals through a three-stage cheap-to-expensive evaluation process and claims better policies than hand-crafted or prior autom...

  11. LLM-as-a-Verifier: A General-Purpose Verification Framework

    cs.AI 2026-07 conditional novelty 5.0

    Expecting over scoring-token logits yields continuous, scalable verification that improves agent trajectory selection and dense RL rewards across coding, robotics, and medical benchmarks.

  12. LLM-as-a-Verifier: A General-Purpose Verification Framework

    cs.AI 2026-07 conditional novelty 5.0

    Computing the expectation over scoring-token logits instead of taking argmax enables verification to scale along granularity, repetition, and criteria decomposition, achieving state-of-the-art on four agentic benchmar...

  13. Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.

  14. LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning

    cs.RO 2025-09 unverdicted novelty 5.0

    LLM-TALE steers RL exploration using LLM-generated plans at task and affordance levels with online suboptimality correction, improving sample efficiency and success rates on pick-and-place tasks without human supervision.

  15. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

    cs.AI 2025-03 unverdicted novelty 2.0

    This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.