cs.AINov 2, 2026

RLiD: Reinforcement Learning in the Decision Plane for Language Agents and LLMs

Authors: Ziyi Chen, Yan Zhang, Jianhui Wei, Jianing Yin, Daoan Zhang

Organizations: University of Illinois Urbana-Champaign. · National University of Singapore. · Zhejiang University. · University of Pennsylvania. · 

Abstract

Reinforcement learning (RL) has improved the capabilities of large language models (LLMs) across a wide range of tasks. However, token-level RL assigns an action's advantage to the entire generated response, including tokens specifying the parsed action, reasoning chains, and malformed content. Although the environment executes only the parsed action, variation in how the action is expressed in natural language can introduce additional variance into policy-gradient estimates. We propose RLiD (Reinforcement Learning in the Decision plane), a framework that directly optimizes the probabilities of executable action options. RLiD compiles observations, an optional compact memory, and a labeled action menu into the model input, and uses a large decision model (LDM) to select an action in a single forward pass. By eliminating autoregressive token generation and bypassing action parsing, RLiD avoids invalid action outputs and improves RL rollout efficiency. Our analysis shows that, within a fixed text policy, marginalizing over alternative realizations of the same action removes a zero-mean gradient component without changing the expected update. We further distill trained LDM policies into generative LLMs through supervision on their action trajectories. Experiments on ARC, Countdown, and Sokoban demonstrate improved performance or lower computational cost across several settings. On ALFWorld, the complete training and distillation pipeline reaches 99.3% success in 12.7 H100 GPU-hours, compared with 86.6% in 17.3 GPU-hours for token-level RL of the same LLM. With compiled memory, our strongest Qwen2.5-1.5B LDM and distilled generative LLM achieve 100% success on all 134 unseen and 140 seen ALFWorld evaluation games.

Figures & tables

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 28, 2026

Dyad: Extending Large Language Models with Native Typed Decision-Making

We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dyad, an architecture that augments a pretrained LLM with an environment-conditioned action encoder that embeds each candidate action description in parallel, then scores these embeddings against the LLM's internal state to yield a distribution over typed actions. By factorizing decision-making into representations of the evolving interaction state and environment-specific action semantics, Dyad introduces an inductive bias for learning reusable representations while keeping action scoring efficient even as the action space grows. We investigate two complementary reinforcement learning settings driven by environment interaction. With the LLM frozen, training the action encoder alone achieves consistent gains across four unseen environments, enabling modular adaptation without modifying any LLM parameters. Jointly optimizing both components outperforms conventional RL post-training across diverse interactive tasks and model scales, including a 3.80% average absolute gain on ALFWorld with a 9B model, while improving general knowledge, reasoning, and coding.
Feb 20, 2026

Not all tokens are needed(NAT): token efficient reinforcement learning

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length into a hidden tax on RL. We introduce Not All Tokens Are Needed (NAT), a unified framework that makes the token budget a first-class optimization primitive. NAT updates the policy using only a selected subset of generated tokens while preserving the learning signal of full-sequence RL. The core idea is an unbiased partial-token policy-gradient estimator via Horvitz-Thompson reweighting, which ensures statistically correct gradients despite subsampling. We instantiate NAT with two simple, plug-and-play token selection schemes: Uniform Random Sampling (URS) and Random Prefix Cutting (RPC), both of which reduce forward and backward compute and memory without modifying the reward computation or rollout pipeline. Across mathematical reasoning benchmarks, NAT matches full-token GRPO performance while using as few as 50% of tokens, providing an efficient and orthogonal pathway to scaling RL beyond the limits imposed by long trajectories. In our experiments, RPC saves 18% peak GPU memory and 29% forward and backward RL training time for Qwen3-8B.
Mar 27, 2026

Distributionally Robust Token Optimization in RLHF

Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on multi-step reasoning problems. To address this problem, we propose a Distributionally Robust Token Optimization (DRTO) approach, which combines token-level Reinforcement Learning from Human Feedback (RLHF) with Distributionally Robust Optimization (DRO). DRTO constructs f-divergence ambiguity sets over span-level actor losses, providing a principled way to emphasize difficult response segments during policy optimization. Empirically, DRTO enhances consistency under distribution shifts in multiple reasoning benchmarks among different tasks, achieving +4.4+4.4 percentage points on MATH-500 and +2.7+2.7 percentage points on LiveCodeBench over standard RTO.