REVIEW 20 cited by
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
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
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
read the original abstract
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs and it remains unclear how to develop such algorithms. To study this, we first introduce a new benchmark, ColBench, where an LLM agent interacts with a human collaborator over multiple turns to solve realistic tasks in backend programming and frontend design. Building on this benchmark, we propose a novel RL algorithm, SWEET-RL (RL with Step-WisE Evaluation from Training-time information), that uses a carefully designed optimization objective to train a critic model with access to additional training-time information. The critic provides step-level rewards for improving the policy model. Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms, enabling Llama-3.1-8B to match or exceed the performance of GPT4-o in realistic collaborative content creation.
Forward citations
Cited by 20 Pith papers
-
Unlocking Proactivity in Task-Oriented Dialogue
Introduces a Cognitive User Simulator modeling stratified personas with hidden concerns and Simulator-Induced Asymmetric-View Policy Optimization to unlock proactive behavior in task-oriented dialogue agents.
-
CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.
-
PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
PRIME enables agents to proactively reason in user-centric tasks by iteratively evolving structured memories from interaction trajectories without gradient-based training.
-
ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
ActivityEditor introduces a dual-LLM-agent system with reinforcement learning that produces statistically faithful and physically valid human mobility trajectories in zero-shot cross-regional settings.
-
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
Iterative Reward Calibration with MT-GRPO and GTPO enables effective multi-turn RL for tool-calling agents, raising Tau-Bench success from 63.8% to 66.7% for a 4B model and from 58.0% to 69.5% for a 30B model.
-
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
MetaEvolve trains LLMs with reinforcement learning on synthesized code-refinement trajectories, reporting large gains on coding and numerical-optimization benchmarks.
-
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
AppWorld-UL perturbs AppWorld's autonomous tasks into 516 user-interaction-requiring tasks; SOTA agents succeed on only 48.6% of them.
-
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
A two-stage probe (hidden-state estimate plus attention-based correction) yields per-step GRPO rewards that survive prefix contamination and beat external-judge and tree-search rewards in the reported benchmarks.
-
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
PAIR combines a hidden-state probe with an attention correction to deliver robust step-level rewards for GRPO-based optimization of multi-turn LLM agents, achieving high AUROC on contaminated trajectories at low cost.
-
Step Rejection Fine-Tuning: A Practical Distillation Recipe
Step Rejection Fine-Tuning masks loss on erroneous steps identified by a critic LLM in unresolved trajectories, raising SWE-bench Verified resolution rate by 3.7% to 32.2% versus 2.4% for trajectory-level rejection.
-
CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
A retail user-simulator benchmark and GRPO training recipe claim improved persona adherence, but the paper's abstract and body disagree on core numbers.
-
Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
Group Causal Counterfactual Policy Optimization trains LLMs on generalizable reasoning by defining episodic rewards for counterfactual robustness and transferability then optimizing the policy with token-level advantages.
-
ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction
ABBEL trains LLM agents to act from a compact natural-language belief state; belief-quality and brevity rewards close most of the gap with full-context agents.
-
Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse
Tree Training serializes tree trajectories via DFS and uses redundancy-free partitioning to compute weighted per-token losses exactly once per token, achieving up to 6.2x training speedup on dense and MoE models.
-
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
RLBoost harvests preemptible GPUs for RL rollout via a hybrid architecture with adaptive offload, pull-based transfer, and token-level migration, delivering 1.51x-1.97x throughput and 28-49% better cost efficiency tha...
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
Unlocking Proactivity in Task-Oriented Dialogue
Introduces a user concern simulator and asymmetric policy optimization to enable proactive behavior in task-oriented dialogues by using latent concerns as a training signal.
-
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a fut...
-
ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning
An episode-level variant of GRPO (ESPO) improves personalized GUI-agent reasoning on the 102-episode SmartSpot benchmark, outperforming step-wise and outcome-only training baselines.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applicat...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.