Related papers: Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems

Related papers

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
arXiv Detail & Related papers (2026-06-04T07:15:43Z)
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning [65.58724910851039]
Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models.<n>We find that this paradigm still underperforms other paradigms in some aspects.<n>We introduce RWKU+, an extended benchmark equipped with novel trade-off metrics and gradient-level diagnostic tools.
arXiv Detail & Related papers (2026-05-26T14:34:14Z)
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
arXiv Detail & Related papers (2026-05-17T14:09:35Z)
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments [60.3427704389541]
Large Language Models are being increasingly deployed as the decision-making core of autonomous agents.<n>Yet, in conversational benchmarks, these agents frequently fail due to the cascading effects of incorrect decision-making.<n>We present the Failure-Aware Meta-Agentic framework to tackle these challenges.
arXiv Detail & Related papers (2026-04-28T02:21:53Z)
Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision [11.159231524113764]
Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose the textbfGuided Verifier framework to address these structural limitations.<n>We develop a specialized data synthesis pipeline targeting multimodal hallucinations, constructing textbfCoRe dataset of process-level negatives and textbfCorrect-guide textbfReasoning trajectories to train the guided verifier.
arXiv Detail & Related papers (2026-02-04T07:38:42Z)
Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning [26.401906729658688]
Agentic Reinforcement Learning (ARL) focuses on training large language models to interleave reasoning with external tool execution to solve complex tasks.<n>Most existing ARL methods train a single shared model parameters to support both reasoning and tool use behaviors, implicitly assuming that joint training leads to improved overall agent performance.<n>We show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization.<n>We propose Disentangled Action Reasoning Tuning(DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool-use via separate low-rank
arXiv Detail & Related papers (2026-02-01T03:19:22Z)
On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
arXiv Detail & Related papers (2026-01-29T17:48:56Z)
Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning [58.432996881401415]
Recent work augments large language models (LLMs) with external tools to enable agentic reasoning.<n>We propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt.<n>STA generates benign-looking prompt rewrites from the original one with high semantic fidelity.
arXiv Detail & Related papers (2026-01-24T19:36:51Z)
The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
arXiv Detail & Related papers (2026-01-19T11:45:39Z)
Internal Representations as Indicators of Hallucinations in Agent Tool Selection [5.2107604548805915]
Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage.<n>LLMs suffer from hallucinations where they choose incorrect tools, provide malformed parameters and exhibit 'tool bypass' behavior.<n>We present a computationally efficient framework that detects tool-calling hallucinations in real-time by leveraging LLMs' internal representations.
arXiv Detail & Related papers (2026-01-08T18:38:45Z)
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench [58.114899897566964]
In a multi-turn conversational environment, large language models (LLMs) often struggle with consistent reasoning and adherence to domain-specific policies.<n>We propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules.<n>IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively.
arXiv Detail & Related papers (2025-08-28T15:57:33Z)
Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios [54.58186816693791]
environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption.<n>We propose a new mechanism, converting the fine-tuning process to a specific- parameter generation.<n>In particular, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components.
arXiv Detail & Related papers (2025-06-30T17:14:12Z)
Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
arXiv Detail & Related papers (2025-05-26T14:42:35Z)
Leveraging LLM Inconsistency to Boost Pass@k Performance [3.797421474324735]
Large language models (LLMs) achieve impressive abilities in numerous domains, but exhibit inconsistent performance in response to minor input changes.<n>We introduce a novel method for leveraging models' inconsistency to boost Pass@k performance.<n>Specifically, we present a "Variator" agent that generates k variants of a given task and submits one candidate solution for each one.
arXiv Detail & Related papers (2025-05-19T10:22:04Z)
The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks [56.37880529653111]
The demand for large computation model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications.<n>In this paper, we investigate the LAIM-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment.
arXiv Detail & Related papers (2025-05-14T08:18:55Z)
Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models [55.46269953415811]
We identify ToM-sensitive parameters and show that perturbing as little as 0.001% of these parameters significantly degrades ToM performance.<n>Our results have implications for enhancing model alignment, mitigating biases, and improving AI systems designed for human interaction.
arXiv Detail & Related papers (2025-04-05T17:45:42Z)
A Unified Virtual Mixture-of-Experts Framework:Enhanced Inference and Hallucination Mitigation in Single-Model System [9.764336669208394]
Generative models, such as GPT and BERT, have significantly improved performance in tasks like text generation and summarization.<n>However, hallucinations "where models generate non-factual or misleading content" are especially problematic in smaller-scale architectures.<n>We propose a unified Virtual Mixture-of-Experts (MoE) fusion strategy that enhances inference performance and mitigates hallucinations in a single Qwen 1.5 0.5B model.
arXiv Detail & Related papers (2025-04-01T11:38:01Z)
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
arXiv Detail & Related papers (2025-02-18T15:45:01Z)
Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging [11.708743111945727]
Large Language Models (LLMs) have demonstrated impressive capabilities, but their high computational costs pose challenges for customization.<n>Model merging offers a cost-effective alternative, yet existing methods suffer from interference among parameters, leading to performance degradation.<n>We propose Optimal Brain Iterative Merging, a novel method designed to mitigate both intra-model and inter-model interference.
arXiv Detail & Related papers (2025-02-17T09:07:49Z)
Mitigating Parameter Degeneracy using Joint Conditional Diffusion Model for WECC Composite Load Model in Power Systems [2.7212274374272543]
We develop a joint conditional diffusion model-based inverse problem solver (JCDI) JCDI incorporates a joint conditioning architecture with simultaneous inputs of multi-event observations to improve parameter generalizability. Simulation studies on the WECC CLM show that the proposed JCDI effectively reduces uncertainties of degenerate parameters.
arXiv Detail & Related papers (2024-11-15T18:53:08Z)
SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
arXiv Detail & Related papers (2024-08-19T17:32:15Z)
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models [32.95155349925248]
We propose a modular paradigm ReWOO that detaches the reasoning process from external observations, thus significantly reducing token consumption. We show that ReWOO achieves 5x token efficiency and 4% accuracy improvement on HotpotQA, a multi-step reasoning benchmark. Our illustrative work offloads reasoning ability from 175B GPT3.5 into 7B LLaMA, demonstrating the significant potential for truly efficient and scalable ALM systems.
arXiv Detail & Related papers (2023-05-23T00:16:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.