4 citations · 21 across the 53 of their papers we have counts for
58 papers
VeriEvolve: Evaluator-First Evolution for Tool-Using Agents
Yueshen Li, Kamer Ali Yuksel, Gokhan Tur +2
A central obstacle to self-improving agents is the absence of a reliable fitness signal for realistic stateful tasks. We introduce \textsc{VeriEvolve}, an evaluator-first evolution…
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
Pardis Sadat Zahraei, Janvijay Singh, Gokhan Tur +1
Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between capability and alignment, and bet…
When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
Janvijay Singh, Vaishnavi Shrivastava, Dilek Hakkani-Tur +2
LLM agents increasingly solve long-horizon tasks by autonomously interacting with their environment. In doing so, their strategies rely on assumptions about that environment: which…
Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training
Emre Can Acikgoz, Yang Li, Zeyu Leo Liu +4
Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage pipelines,…
Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does
Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur +5
Prosodic cues can carry task-relevant information that words omit, but existing benchmarks rarely test whether it changes downstream decisions. We introduce Hear2Act, a 480-scenari…
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür +1
Multi-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tasks through role specialization and structured interaction. Howe…
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Jiayu Liu, Qihan Lin, Cheng Qian +8
LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environme…
ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
Jinu Lee, Shivam Agarwal, Amruta Parulekar +3
Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the re…
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian +7
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often co…
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Vardhan Dongre, Joseph Hsieh, Viet Dac Lai +3
Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This d…
Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?
Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson +2
Synthetic accented speech is a promising way to improve automatic speech recognition (ASR) when real accented recordings are scarce. We ask what makes such data useful for ASR fine…
Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah +5
Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model's opinion. While prior work has mostly studied this in singl…
Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration
Priyanka Kargupta, Shuhaib Mehri, Dilek Hakkani-Tur +1
Despite interdisciplinary research leading to larger and longer-term impact, most work remains confined to single-domain academic silos. Recent AI-based approaches to scientific di…
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha +2
Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling e…
ReIn: Conversational Error Recovery with Reasoning Inception
Takyoung Kim, Jinseok Nam, Chandrayee Basu +5
Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to una…
ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
Yifei Zhang, Hooshang Nayyeri, Rinat Khaziev +5
Agentic task-oriented dialogue (TOD) requires systems to track concurrent goals, dependencies, and long-horizon state. We examine goal-lifecycle recovery from fixed dialogue trajec…
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer…
DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference
Parisa Rabbani, Priyam Sahoo, Ruben Mathew +4
LLMs are increasingly used as third-party judges, yet their reliability when evaluating speakers in dialogue remains poorly understood. We show that LLMs judge identical claims dif…
MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration
Shuhaib Mehri, Priyanka Kargupta, Tal August +1
As conversational agents accumulate experience collaborating with users, adapting to user preferences is essential for fostering long-term relationships and improving collaboration…
SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
Emre Can Acikgoz, Jinoh Oh, Jie Hao +7
Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providi…
MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
Emre Can Acikgoz, Jinoh Oh, Joo Hyuk Jeon +7
Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applicat…
Drift No More? Context Equilibria in Multi-Turn LLM Interactions
Vardhan Dongre, Ryan A. Rossi, Viet Dac Lai +3
Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where…
From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
Parisa Rabbani, Nimet Beyza Bozdag, Dilek Hakkani-Tür
LLMs are increasingly employed as judges across a variety of tasks, including those involving everyday social interactions. Yet, it remains unclear whether such LLM-judges can reli…
Self-Improving LLM Agents at Test-Time
Emre Can Acikgoz, Cheng Qian, Heng Ji +2
One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize t…