5/6 🙌 Huge thanks to our contributors: @binwu_cs , @srahmanidashti , @TEKnologyy , Arastun Mammadli, @QSFByte , Xiao Fu, @VarshaMath , Xiaoyu Zhang, @ChuanMg , @g_drayson , @a_chowdhury99 , @JeromeRamos70 , Abdine Maiga, and Emine Yilmaz.

4/6 Our focus includes open and evolving agent ecosystems, where candidate systems range from tools and single/multi-agent systems and dynamically composed solutions. Key challenges include capability modeling, uncertainty, utility estimation, composition, and evaluation.

3/6 🧭 We organize the literature across an end-to-end pipeline: task understanding → discovery, representation & indexing → retrieval, reranking & selection → evaluation. We also examine safety, fairness, security, personalization, and transparency.

2/6 🔎 We frame Agent and Tool Search as a task-oriented retrieval and decision-making problem over executable systems—not static documents. Suitability depends on capability, competence, reliability, safety, cost, and downstream task performance.

Looking forward to presenting our works!

📚ICML 2026 From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization openreview.net/pdf?id=pXF0pu…

📚 ACL 2026 Beyond Static Toolsets: Self-Evolving LLM Tool Agents via Continual Documentation Adaptation aclanthology.org/2026.findin… Structured Dialogue Refinement: Building Retrieval-Augmented Question Answering on Goal-Oriented Dialogues aclanthology.org/2026.findin…

I’m a PhD student at UCL @uclcs , affiliated with the UCL NLP Group @ucl_nlp and the UCL Centre for AI @ai_ucl . My research focuses on LLM agents, orchestration systems, agent evaluation & diagnosis, and agent/tool search. Find more on my personal website.

1st author Paper: “From Interaction Trajectories to Prompt Rules: Credit Assignment for Multi-Agent Prompt Optimization” → Trajectory-aware credit assignment for multi-agent systems → Enables localized, iterative prompt rule refinement #MultiAgentSystems #LLM #AIAget

Excited to share that the deadline for our AgentSearch Workshop @ SIGIR 2026 has been extended to 📅 𝗠𝗮𝘆 𝟴, 𝟮𝟬𝟮𝟲 (𝗔𝗼𝗘) If you work on retrieval, AI agents, or tool use, we’d love to see your submissions. 🔗 agent-search.github.io/agent…

Excited to share that 3 of my papers are accepted to #ACL2026 🎉 I’m fortunate to contribute as a main author (1st/2nd author) across these works: • 𝗕𝗲𝘆𝗼𝗻𝗱 𝗦𝘁𝗮𝘁𝗶𝗰 𝗧𝗼𝗼𝗹𝘀𝗲𝘁𝘀: 𝗦𝗲𝗹𝗳-𝗘𝘃𝗼𝗹𝘃𝗶𝗻𝗴 𝗟𝗟𝗠 𝗧𝗼𝗼𝗹 𝗔𝗴𝗲𝗻𝘁𝘀 𝘃𝗶𝗮 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗮𝗹 𝗗𝗼𝗰𝘂𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗔𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻 (Findings) Follow-up to my ACL work last year (paper: aclanthology.org/2025.findin…), we study how LLM agents adapt to evolving tool ecosystems via continual documentation adaptation. • 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗗𝗶𝗮𝗹𝗼𝗴𝘂𝗲 𝗥𝗲𝗳𝗶𝗻𝗲𝗺𝗲𝗻𝘁: 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗥𝗔𝗚 𝗼𝗻 𝗚𝗼𝗮𝗹-𝗢𝗿𝗶𝗲𝗻𝘁𝗲𝗱 𝗗𝗶𝗮𝗹𝗼𝗴𝘂𝗲𝘀 (Findings) My internship work at Bloomberg — we adapt goal-oriented dialogues for retrieval-augmented QA. • 𝗠𝗶𝘁𝗶𝗴𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗜𝗻𝘁𝗲𝗿𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗳𝗼𝗿 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗮𝗻𝗱 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗦𝗲𝗮𝗿𝗰𝗵 𝗔𝗴𝗲𝗻𝘁𝘀 (Main) We investigate context interference in multi-turn search agents and propose a refinement-based solution. Also sharing: 𝗣𝗥𝗘𝗙: 𝗥𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲-𝗙𝗿𝗲𝗲 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗼𝗳 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘀𝗲𝗱 𝗧𝗲𝘅𝘁 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗟𝗟𝗠𝘀 (not accepted this time) A framework for evaluating personalised LLM outputs without requiring references Grateful to my supervisors, collaborators, and teammates, especially my supervisor Emine @emine_yilm and Edgar @edgarmeij , my internship team lead @myahya , and my collaborators Boyang @BeyondHsueh 🙏 #ACL2026 #NLP #LLM #AIAgents #ToolUse #RAG #MachineLearning #AIResearch

Our AgentSearch@SIGIR 2026 CFP is out! We’re looking for work on searching and selecting AI agents/tools, including: • agent capability representation • agent retrieval & ranking • evaluation & benchmarking • responsible agent search Submission types: • Extended abstracts (2 pages) • Research / Perspective / Demo papers (4–9 pages) 📅 Deadline: Apr 15, 2026 (AoE) Details 👇 agent-search.github.io/agent…