arXiv subjects

Yihan Jiao

Publications and source records attributed to Yihan Jiao.

9 recordsLinked to original sources

arXiv2026

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent's search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20% while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model's overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design.

cs.AI↗

arXiv2026

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accuracy; (2) listwise methods capture global context but suffer from context-window constraints and prohibitive inference latency. To address these issues, we propose GroupRank, a novel paradigm that balances flexibility and context awareness. To unlock the full potential of groupwise reranking, we propose an answer-free data synthesis pipeline that fuses local pointwise signals with global listwise rankings. These samples facilitate supervised fine-tuning and reinforcement learning, with the latter guided by a specialized group-ranking reward comprising ranking-utility and group-alignment. These complementary components synergistically optimize document ordering and score calibration to reflect intrinsic query-document relevance. Experimental results show GroupRank achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED, while delivering a 6.4$\times$ inference speedup.

cs.IR↗

arXiv2026

CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely on external rewards that often fail to evaluate document faithfulness, and may misjudge similar answers in open-domain settings. In addition, there is no RAG-based selfreward mechanism. Moreover, although such a mechanism could in principle estimate answer confidence given documents, the absence of objective feedback in a self-judgment can cause hallucination accumulation and eventual model collapse. To tackle these issues, we propose a novel "internal-external" hybrid reward framework centered on a Contrastive Likelihood Reward (CLR). CLR directly optimizes the log-likelihood gap between responses conditioned on prompts with and without supporting evidence. This encourages the model to extract relevant evidence and increases its confidence when grounded in a specific context. Experiments show that our method (used alone or combined with external correctness rewards) achieves strong performance on singlehop, multi-hop, vertical-domain, and faithfulness benchmarks. Our training code and models are coming soon.

cs.CL↗

arXiv2025

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

The Retrieval-Augmented Generation (RAG) approach enhances question-answering systems and dialogue generation tasks by integrating information retrieval (IR) technologies with large language models (LLMs). This strategy, which retrieves information from external knowledge bases to bolster the response capabilities of generative models, has achieved certain successes. However, current RAG methods still face numerous challenges when dealing with multi-hop queries. For instance, some approaches overly rely on iterative retrieval, wasting too many retrieval steps on compound queries. Additionally, using the original complex query for retrieval may fail to capture content relevant to specific sub-queries, resulting in noisy retrieved content. If the noise is not managed, it can lead to the problem of noise accumulation. To address these issues, we introduce HANRAG, a novel heuristic-based framework designed to efficiently tackle problems of varying complexity. Driven by a powerful revelator, HANRAG routes queries, decomposes them into sub-queries, and filters noise from retrieved documents. This enhances the system's adaptability and noise resistance, making it highly capable of handling diverse queries. We compare the proposed framework against other leading industry methods across various benchmarks. The results demonstrate that our framework obtains superior performance in both single-hop and multi-hop question-answering tasks.

cs.CL↗

arXiv2025

PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination of a given query and retrieved documents is crucial. However, most benchmarks focus on overall RAG system performance, rarely assessing LLM-specific capabilities. Current benchmarks emphasize broad aspects such as noise robustness, but lack a systematic and granular evaluation framework on document utilization. To this end, we introduce \textit{Placeholder-RAG-Benchmark}, a multi-level fine-grained benchmark, emphasizing the following progressive dimensions: (1) multi-level filtering abilities, (2) combination abilities, and (3) reference reasoning. To provide a more nuanced understanding of LLMs' roles in RAG systems, we formulate an innovative placeholder-based approach to decouple the contributions of the LLM's parametric knowledge and the external knowledge. Experiments demonstrate the limitations of representative LLMs in the RAG system's generation capabilities, particularly in error resilience and context faithfulness. Our benchmark provides a reproducible framework for developing more reliable and efficient RAG systems. Our code is available in https://github.com/Alipay-Med/PRGB.

cs.CL↗

arXiv2024

Evidence for multiband gapless superconductivity in the topological superconductor candidate 4Hb-TaS2

We present the ultralow-temperature thermal conductivity measurements on single crystals of transition-metal dichalcogenide material 4Hb-TaS$_{2}$, which has recently been proposed as a topological superconductor candidate. In zero field, a small residual linear term $κ_{0}/T$ is observed, indicating the existence of a residual density of states in the superconducting state. The slow field dependence of $κ_{0}/T$ at low fields rules out the presence of nodes in the superconducting gap, and the S-shaped field dependence across the full field range suggests multiple superconducting gaps in 4Hb-TaS$_{2}$. Our results provide evidence for multiband gapless superconductivity in 4Hb-TaS$_{2}$, and the residual density of states come from certain gapless Fermi surfaces.

cond-mat.supr-con↗

arXiv2024

Gapped quantum spin liquid in a triangular-lattice Ising-type antiferromagnet PrMgAl11O19

In the search of quantum spin liquid (QSLs), spin-1/2 triangular-lattice Heisenberg antiferromagnets (TLHAFs) have always been viewed as fertile soils. Despite the true magnetically-ordered ground state, anisotropy has been considered to play a significant role in stabilizing a QSL state. However, the nature and ground state of the most anisotropic case, the triangular-lattice Ising antiferromagnet (TLIAF), remains elusive and controversial. Here, we report specific heat and thermal conductivity measurements on a newly-discovered Ising-type QSL candidate PrMgAl11O19. At zero field, the magnetic specific heat shows a quadratic temperature dependence. On the contrary, no direct positive magnetic contribution to thermal conductivity was detected, ruling out the presence of mobile gapless fermionic excitations. Further analysis of phonon thermal conductivity reveals that the phonons are strongly scattered by thermally-activated magnetic excitations out of a gap, which exhibits a linear dependence with magnetic field. These results demonstrate that the spin-1/2 TLIAF PrMgAl11O19 has a gapped Z2 QSL ground state.

cond-mat.str-el↗

arXiv2024

Discovery of universal phonon thermal Hall effect in crystals

Thermal Hall effect (THE) in insulator is a remarkable phenomenon that arises from the motion of chargeless quasi-particles under a magnetic field. While magnons or exotic spin excitations were considered as the origin of THE in some magnetic materials, there are more and more evidences suggesting that phonons play a significant role. However, the mechanism behind phonon THE is still unknown. Here we report the observation of THE, including planar THE, in a broad range of non-magnetic insulators and semiconductors: SrTiO3, SiO2 (quartz), MgO, MgAl2O4, Si and Ge. While the presence of antiferrodistortive domains in SrTiO3 and chiral phonons in SiO2 may complicate the interpretation of THE, the striking observations of THE in trivial insulators MgO and MgAl2O4, as well as in high-purity intrinsic semiconductors Si and Ge, demonstrate that phonon THE is a universal property of crystals. Without other effects on phonons such as from magnons, this universal phonon THE is characterized by a scaling law of |\k{appa}_xy| ~ \k{appa}_xx^2. Our results experimentally discover a fundamental physics of phonons in magnetic field, which should come from the direct coupling between atom vibrations and the field. Starting from this universal phonon THE in crystals, all previous interpretations of THE in magnetic or non-magnetic materials need to be reconsidered.

cond-mat.str-el↗

arXiv2023

Multigap nodeless superconductivity in the topological semimetal PdTe

Recently PdTe was identified as a spin-orbit coupled topological Dirac semimetal and was claimed to exhibit both bulk-nodal and surface-nodeless superconducting gaps. Here we report the ultralow-temperature thermal conductivity measurements on PdTe single crystals with $T_c$ = 4.5 K to investigate its superconducting gap structure. It is found that the residual linear term $κ_0/T$ is negligible in zero magnetic field. Furthermore, the field dependence of $κ_0(H)/T$ exhibits an $\sf S$-shaped curve. These results suggest that PdTe has multiple nodeless superconducting gaps, which is at odds with the claimed bulk-nodal gap. The reason for the discrepancy is likely that previous angle-resolved photoemission spectroscopy measurements were only performed down to 2 K and cannot observe the smaller nodeless gap. The fully gapped superconducting state in PdTe is compatible with it being a topological superconductor candidate.

cond-mat.supr-con↗