Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central qu...
This work proposes a family of symmetric multi-player alignment games and proves that any symmetric Nash equilibrium policy of the $(k+1)-player alignment game achieves the optimal $(k,\frac{k}{k+1})$-robust alignment.
This work proposes an approach that recasts the task as automated knowledge base construction: prompting an LLM to synthesize a 3NF-compliant relational schema from Wikipedia infobox timelines, populating the schema to obtain a queryable database, and generating and executing SQL queries against it, with QA accuracy se...
In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by separating events that happened at different times, this work probes the ability...
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A novel threat is unveiled in which attackers steer the RAG system's response by injecting malicious passages into its knowledge base, enabling the attacker to steer the response without altering the user input or modifying the RAG weights.
Jiaqi Xue, Meng Zheng, Yebowen Hu et al.· arXiv.org· 109 citations· ⚡8
The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems, covering the full stack from first principles to production deployment. The central thesis: building great agentic systems requires understanding every layer of the pipeline, not just one. The book opens...
This work identifies the first token of the response as a structurally distinct target for diversification, largely overlooked in prior work, and finds that the first-token distribution is sharply concentrated and only weakly related to downstream correctness, as lower-probability candidates can yield similarly accurat...
This paper systematically investigates two principal test-time scaling axes of LLM agents: sequential scaling through extended interaction and parallel scaling through trajectory sampling, and finds that neither scaling axis can consistently yield meaningful gains from additional test-time compute in realistic environm...
Xiao-Chuan Li, Ryan Ming, P. Setlur et al.· 23 citations· ⚡1
STEPQuant is proposed, a spatial-temporal post-training quantization framework for Delta-rule recurrent states that allocates precision according to error magnitude and memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error.
Bing-Chen Yao, Hao-Bo Xu, Hao-Kun Lin et al.· 0 citations
GEB is introduced, a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment and demonstrating improvements over prior memory frameworks in both multiple-choice and open-ended question answ...
Hui-Hui Ren, Lei Fan, Henry Pao et al.· 0 citations
An explanation of how hybrid models of this sort can implicitly encode position at global NoPE layers is developed, and insights are provided for how to encode position in a way that can extrapolate to longer sequence lengths indefinitely.
Cutter Dawes, Nick Alonso, Tomas Figliolia et al.· 0 citations
Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthetic grade-school mat...
Ratish Puduppully, Pranabendu Misra, Paarth Iyer et al.· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
