T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler

Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL framework called Task-Specific feature Selector and Scheduler (T3S), which consists of two components: a feature selector and a task scheduler. Specifically, the feature selectors employ hypernetworks to construct task-specific soft masks, which can be applied by globally shared representation to construct task-specific features. The task scheduler selects tasks for learning through two metrics, where the selection probability is inversely proportional to task progress (e.g., success rate) and task learning speed. Experimental results show that T3S consistently outperforms the state-of-the-art MTRL algorithms on various robotics manipulation tasks.

PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs

Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed or manually designed task mixtures, even though task usefulness changes as training progresses. Online curriculum methods often define learnability by update magnitude, ignoring whether the update translates into reward gains, which can misallocate rollout budget toward tasks with large but ineffective updates. We propose PAC, a Progress-Augmented Advantage Curriculum for multi-task RL of LLMs that combines two task-level signals: advantage-derived learnability, which measures the magnitude of the policy update a task can induce, and recent reward gains, which show whether those updates have improved task performance. A Bayesian Thompson Sampling controller uses these signals to allocate rollouts across tasks during GRPO training. We evaluate PAC under two settings: a multi-level reasoning setting and a multi-domain reasoning setting. PAC improves sample efficiency and final performance: it reaches comparable validation scores with fewer rollout steps and achieves higher final averages than random sampling and advantage-based curriculum baselines in both settings. These results show that jointly tracking advantage signals and actual reward gains yields an effective online curriculum for LLM post-training.

Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independent episodes, while existing approaches to skill learning either focus on repeated attempts of one task or use pipelines with multiple stages that entangle extraction, retrieval, and execution. We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks. SkillRise organizes related instances into progressively challenging sequences and uses a single policy to alternate between task solving and curating an evolving skill document passed directly to the next task. Decoupled credit assignment across tasks supervises solving with the current task outcome and curation with discounted downstream outcomes. Experiments on ALFWorld, WebShop, and ScienceWorld show that SkillRise achieves the strongest Pass@1 performance among the compared methods, with gains over the strongest baseline ranging from 2.3 to 8.5 percentage points. Although trained across distinct tasks, its learned curation policy remains effective for repeated attempts on the same task. Further analysis reveals scaling at test time across tasks: performance improves with longer sequences of related tasks even when each task is attempted only once. This trend suggests that SkillRise reuses transferable skills across tasks rather than benefiting from repeated sampling of the same task. SkillRise further retains strong performance while substantially reducing the runtime overhead of skill learning pipelines with multiple stages. Together, these results provide a simple and efficient training paradigm for LLM agents to extract, refine, and reuse transferable skills across tasks.

Training Language Models to Cooperate with Inference-Time Controllers

Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning. Existing post-training methods, however, typically optimize for a single fixed interaction pattern, despite real deployments relying on diverse controllers such as Chain-of-Thought, self-consistency, debate, planning, and verification pipelines. This creates a training--deployment mismatch and limits transfer to new workflows. We introduce CALM (Controller-Aware Language Models), a post-training framework that explicitly places controllers in the training loop. We formulate controller-aware post-training as multi-task reinforcement learning over controller-induced interaction protocols, where controllers are compositions of reusable local reasoning modules. This structure also induces a module-level decomposition of mixed-controller training under a turn-level GRPO objective, enabling a systematic study of controller and module-aware training strategies. We evaluate CALM on held-out controller compositions and broader controller shifts, showing that controller-aware post-training improves generalization across inference-time workflows beyond single-controller optimization.

When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis

Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge independently released agents precisely because a joint model is unavailable. We build the missing comparison. Training difficulty-1 and difficulty-2 Qwen3-8B specialists on the AppWorld agent benchmark with LOOP, we merge them (TIES, RAM+) and pit the result against a jointly trained model on the same data. On task-goal completion, merging matches joint RL -- and every merge variant is statistically indistinguishable. To explain why merge method does not matter here, we measure the geometry of the specialists' task vectors, which carries no task-sampling noise: they are near-orthogonal (cosine 0.06 - 0.10) despite ~65% support overlap, a small, shared direction that grows over training and that we calibrate against a random-init floor and a same-run ceiling to confirm it reflects learning, not the low-rank parameterization. Because direction and support are decoupled, support and sign-based merging (RAM, TIES) collapse to near-uniform averaging. We release all code and statistics.

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks can, in turn, push easier tasks back toward high-entropy exploration. This back-and-forth interaction creates inter-task entropy crossovers and frequent entropy spikes. Inspired by this observation, we introduce Entropy Pacing Policy Optimization (EPPO) for multi-task agentic LLMs, which coordinates entropy across tasks to stabilize multi-task optimization. At the core of EPPO is a task-wise dynamic clipping mechanism that replaces the fixed clipping threshold in Group Relative Policy Optimization (GRPO) with a task entropy-aware adaptive bound, tightening updates for over-confident tasks while relaxing them for under-explored ones. Experiments on the multi-task agentic benchmarks demonstrate that the proposed EPPO yields results superior to its counterparts.

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions. Inspired by these advances, we investigate whether a unified transformer policy can be trained across large collections of heterogeneous reinforcement learning environments. We introduce LDM-v0, a Large Decision Model trained offline on trajectories collected from thousands of environments spanning multiple domains and modalities. LDM-v0 is a multi-task, multi-modal transformer policy conditioned on histories of observations, actions, rewards, and termination signals, and trained through supervised next-action prediction over offline trajectories. We describe the environment infrastructure, automated data generation pipeline, model architecture, and training methodology used to build LDM-v0, and evaluate its performance across diverse environments. We show that a single pretrained model matches the performance of independently trained task-specific reference policies on approximately 1,000 environments including robotics, autonomous driving, inventory management, cybersecurity, trading, and video games. These results demonstrate the feasibility of large-scale offline pretraining across heterogeneous reinforcement learning environments using a single transformer policy.

CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion

Perceptive legged locomotion over discontinuous terrain (e.g., stairs, gaps, and obstacles) requires adaptive behavior, as a single conservative gait cannot produce the anticipatory maneuvers needed for abrupt topology changes. Cast as multi-task reinforcement learning, this problem introduces a tension between sharing and separation. Tasks use a common locomotion base but have conflicting rewards, so a policy must share behavior while avoiding value interference. Prior work addresses only one side, with monolithic policies sacrificing specialization and hierarchical sub-policies sacrificing generalization across transitions and unseen terrain. We propose CTS-MoE, which combines a dense mixture-of-experts actor with perception-based gating to compose shared behaviors and a multi-critic with task-specific value heads to prevent interference. The model is trained end-to-end in a single-stage concurrent teacher-student setup that handles partial observability and avoids sequential distillation, with task labels used only during training. At deployment, routing depends solely on perception, allowing terrain adaptation without a high-level selector or terrain classifier. Experiments on a Unitree Go1 in simulation and on hardware across seen and unseen terrains show task-aware specialization, with lower tracking error and higher success rates than monolithic baselines. Project Website: https://cts-moe.github.io/ .

Multi-action Tangled Program Graphs for Multi-task Reinforcement Learning with Continuous Control

Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for specific tasks. To further challenge algorithms, Multi-Task RL (MTRL) environments have been introduced, requiring a single model to learn multiple behaviors. The Tangled Program Graph (TPG) algorithm is a Genetic Programming (GP) algorithm designed for discrete MTRL environments. Recently, the MAPLE algorithm has been proposed, as another GP algorithm that achieves high results in single task continuous RL environments. A variation of the TPG is proposed alongside MAPLE, named Multi-Action TPG (MATPG) that aggregates MAPLE agents, and creates a control flow to activate them. Initially tested on single task RL environments only, MATPG achieved similar results to MAPLE. In this work, we present a new benchmark based on the MuJoCo Half Cheetah from Gymnasium. This benchmark features five distinct obstacles that are randomly positioned in front of the agent, each of which demands a unique behavior. This benchmark serves as a use case for MATPG, to prove its ability as a GP solution for continuous MTRL environments. Our experiments demonstrate its superiority in this multi-task use case when combined with lexicase selection. Furthermore, we examine the interpretability of the evolved graph, revealing that the decision flow of the model is fully interpretable.