# TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs

arXiv: https://arxiv.org/abs/2603.22293 · HTML: https://mlsanity.com/paper/2603.22293/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [RUDDER: Return Decomposition for Delayed Rewards](https://mlsanity.com/paper/1806.07857/) (2018)
- [Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains](https://mlsanity.com/paper/2503.23829/) (2025)
- [An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents](https://mlsanity.com/paper/2505.15117/) (2025)
- [Learning to Reason for Long-Form Story Generation](https://mlsanity.com/paper/2503.22828/) (2025)
- [R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2506.04185/) (2025)

## Built on by (most cited first, 24 of 24)

- [GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation](https://mlsanity.com/paper/2605.11853/) (2026)
- [A Subgoal-driven Framework for Improving Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.19685/) (2026)
- [Training AI Scientists to Replicate Research](https://mlsanity.com/paper/2608.13331/) (2026)
- [OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search](https://mlsanity.com/paper/2604.03675/) (2026)
- [PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization](https://mlsanity.com/paper/2605.17877/) (2026)
- [Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers](https://mlsanity.com/paper/2605.04984/) (2026)
- [PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.09287/) (2026)
- [ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents](https://mlsanity.com/paper/2606.03239/) (2026)
- [Scaling Scientific Discovery Environments for Turn-Level Agentic RL](https://mlsanity.com/paper/2607.28990/) (2026)
- [Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval](https://mlsanity.com/paper/2605.06647/) (2026)
- [Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals](https://mlsanity.com/paper/2606.10684/) (2026)
- [CAFE: Self-Improving Search Agents Need Co-Evolving Feedback](https://mlsanity.com/paper/2608.24794/) (2026)
- [Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context](https://mlsanity.com/paper/2608.17499/) (2026)
- [IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents](https://mlsanity.com/paper/2608.24588/) (2026)
- [PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks](https://mlsanity.com/paper/2609.02236/) (2026)
- [MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development](https://mlsanity.com/paper/2609.36679/) (2026)
- [CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback](https://mlsanity.com/paper/2606.01830/) (2026)
- [EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation](https://mlsanity.com/paper/2606.18235/) (2026)
- [QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents](https://mlsanity.com/paper/2606.32034/) (2026)
- [Toolcompass: Guiding Tool Trialing, Not Suppressing It](https://mlsanity.com/paper/2609.25678/) (2026)
- [PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue](https://mlsanity.com/paper/2609.27987/) (2026)
- [Reinforcement Learning with Verifiable Rewards for Small Search Agents](https://mlsanity.com/paper/2609.28765/) (2026)
- [Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents](https://mlsanity.com/paper/2609.34296/) (2026)
- [SIPO: Selective-Inference Policy Optimization for Tree-Structured Agentic RL](https://mlsanity.com/paper/2609.34805/) (2026)

## Abstract (arXiv)

Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remains a significant challenge. The optimization is often unstable due to sparse rewards and difficult credit assignments across reasoning and tool calls. To address this, we introduce Turn-Level Information Potential Reward Shaping (TIPS), a simple framework that assigns dense, turn-level rewards to each reasoning + tool-call segment based on the increased likelihood of the correct answer under a teacher model. By leveraging the potential-based reward shaping, TIPS offers fine-grained and policy-invariant guidance that overcomes the limitations of outcome-only optimization. Evaluated on seven QA benchmarks, TIPS consistently outperforms GRPO/PPO baselines and substantially improves training stability. For instance, with a Qwen-2.5 7B Instruct model, TIPS improves the average Exact Match score by 11.8% and F1 by 13.6% relative to PPO. Our results demonstrate that turn-level information-potential reward shaping provides an effective and general solution to sparse-reward credit assignment for multi-turn LLM reasoning.